Machine Learning

CIBC Innovation Banking has provided a $30 million growth financing for Aerospike, a real-time database engineered for speed, scale and cost efficiency, powering mission-critical applications across diverse use cases, including Artificial Intelligence (AI) and Machine Learning (ML). This funding will further expand the company’s go-to-market strategy and product innovation.  Aerospike operates at the intersection of the world’s growing data needs and the new opportunities presented by AI and ML. The company’s massively scalable, millisecond-latency database handles vector search, key-value, and graph applications while still running on 80% less infrastructure than legacy or point solutions. Demand for real-time data platform Aerospike said that second quarter of 2024 recurring revenue increased by 51% on a year-over-year basis Aerospike recently announced that second quarter of 2024 recurring revenue increased by 51% on a year-over-year basis, fuelled by the widespread demand for affordable, scalable, and accurate real-time AI. Aerospike enables organisations to manage customer recommendation engines, monetisation, and fraud detection for global organisations.   Subbu Iyer, CEO of Aerospike, said: "This financing is in addition to the $109M investment earlier this year from Sumeru Equity Partners to meet the demand for Aerospike’s real-time data platform, especially for AI. We’re excited to partner with CIBC as we enter our next phase of growth, driving further innovation and investment in our products." AI revolution Youssef Kabbani, Executive Director at CIBC Innovation Banking, said: "AI/ML requires more real-time data than ever before and Aerospike is greatly positioned to meet this demand by providing an infinitely scalable database with high performance and low latency." Youssef Kabbani adds, "We are thrilled to be working with the Aerospike team as they continue to emerge as a main player in the AI revolution."

The new Ericsson Compact Packet Core includes the cloud-native Packet Core Controller (PCC) and Packet Core Gateway (PCG) network functions on top of a compact, one rack, version of Ericsson's Cloud-Native Infrastructure Solution (CNIS).  It is a global solution with pre-defined parameter settings and streamlined migration procedures that simplifies transition to cloud-native and maximises efficient return on investment in this key network infrastructure. Compact Packet Core fully supports 4G, 5G Non-Standalone (NSA), and 5G Standalone (SA) networks, providing CSPs with the capabilities needed to meet their strategic and operational needs. Latest software innovation and security Compact Packet Core is launched with solution lifecycle management service where Ericsson oversees automated upgrades of the network. This brings benefits such as seamless upgrades, and networks that are always up to date with the latest software innovation and security. Monica Zethzon, Head of Solution Area Core Networks, Ericsson, says: “With this solution, we are providing a new approach for upgrading to cloud-native and introducing 5G Core, built on our deep experience with the world’s most advanced networks. It significantly simplifies modernization while unlocking the full potential of our world-class cloud-native software. We are proud to introduce the Ericsson Compact Packet Core for CSPs looking to accelerate their cloud-native journey and manage capacity growth.” Key cloud-native features  New solution delivers the simplicity of the “appliance” approach and adds to it by inheriting the key benefits The new solution delivers the simplicity of the “appliance” approach and adds to it by inheriting the key benefits from being cloud native. It supports key cloud-native features such as automation, In-Service Software Upgrades (ISSU), Container-as-a-Service rolling upgrades (CaaS RU) and gives CSPs the flexibility to adapt the network to new use cases or workloads as they grow and evolve their services to customers. It delivers an optimized and validated configuration for deployment of the packet core network functions on CNIS to maximise ease of deployment, migration, and software upgrades, reducing overall complexity. With the pre-defined configurations of this solution a CSP has 80 percent fewer parameters to adjust when deploying and will enable up to 30% reduction in energy and hardware footprint due to its inbuilt capability to support the latest CPU generations as they evolve. Ericsson Packet Core software  The solution has been created to solve specific challenges that CSPs are facing when transitioning from legacy infrastructure and is designed to simplify operations across the board. It guarantees seamless service continuation and retention of a CSPs business logic underpinning its technological configuration during installation, migration, upgrades, and expansions. The proven Ericsson Packet Core software is used for all deployment scenarios including Compact Packet Core to secure interoperability. Glen Hunt, Principal Analyst at GlobalData says: “It is no secret that CSPs face common and testing challenges when upgrading their cloud deployment models to introduce or expand the benefits of a cloud-native operating model or lead towards the deployment of 5G Core. Ericsson’s Compact Packet Core removes the barrier to deployment that comes with lengthy interoperability and integration testing by virtue of being a pre-integrated solution, and its in-built configurations and reduced footprint demands mean a less costly, complex and time-consuming migration is possible.” Ericsson Mobility Report  Separate Ericsson research in Europe showed consumers are willing to pay up to 15% on top of their ticket The move to cloud-native is well underway, with growing momentum evident in the market. As of October 2024, Ericsson has 120+ unique 5G Core or cloud-native commercial contracts, with 55+ live dual-mode 5G Core solution customers (including EPC, 5G NSA, and 5G SA live customers). Also clear is the growing appetite for 5G SA. Ericsson Mobility Report research indicates close to 60% of 5G subscriptions - 3.6 billion - will be 5G SA in 2030.  Separate Ericsson research in Europe showed consumers are willing to pay up to 15% on top of their ticket to improve their connectivity and app experience at large events such as concerts or sporting occasions. 5G SA best allows CSPs to meet this requirement by introducing differentiated connectivity offerings like reserving a part of their network to provide assured quality of experience for specific users or apps. Ericsson dual-mode 5G Core solution Ericsson was recently placed as a pioneer in the Market Landscape: Core Vendors 2024 report from analyst house Omdia, with the highest overall portfolio score of the vendors assessed having the top spot in both cloud native readiness, automation, and policy and charging. It was also named a Leader in the 2024 Gartner® Magic Quadrant™ for CSP 5G Core Network Infrastructure Solutions, and named top of Frost Radar™ 5G network infrastructure market ranking for the fourth year running in an analysis that covers RAN, transport and core networks. Ericsson currently powers 37 of the world’s 60+ commercially live 5G SA networks, with its RAN solutions and the cloud-native Ericsson dual-mode 5G Core solution.

IT services and solutions provider, Roc Technologies, has announced the launch of its Security Operations Centre (SOC), advancing its mission to provide accessible cyber security solutions to businesses and public sector organisations of all sizes across the UK. The SOC offers 24/7/365 monitoring and tailored security services that enhance resilience against the growing landscape of increasingly sophisticated cyber threats. A modular and scalable approach enables small and mid-sized organisations through to enterprise businesses to navigate challenges with cost, complexity and limited internal expertise, often making high-level protection unattainable. UK data sovereignty laws The service aligns with stringent UK data sovereignty laws, assuring all data is managed  The SOC is operated in-house by Roc Technologies’ UK-based, highly qualified team of skilled analysts and engineers, which differentiates the service from competitors that rely on outsourced, non-UK-based capabilities. 80% of Roc’s delivery teams are fully security-vetted, and the centre operates 24/7, 365 days a year, providing real-time monitoring, threat detection and incident response. The service aligns with stringent UK data sovereignty laws, ensuring all data is stored, managed and monitored within the country’s borders. By allowing customers to select services that complement their existing capabilities, the SOC offers an alternative to traditional, one-size-fits-all solutions. This unique model enables organisations to strengthen their defences while remaining cost-effective and operationally efficient. Cyber security services Chelsea Chamberlin, CTO at Roc Technologies, comments: “The launch of our SOC is proof of our commitment to making high-quality cyber security services accessible to a wide range of organisations." "The stakes are higher than ever, and businesses need solutions that protect against threats without disrupting their operations. Our SOC has been designed to integrate seamlessly with our customers’ existing IT landscapes, ensuring that they can rely on us for protection, resilience and peace of mind.” Benefits from cutting-edge protection The launch builds on Roc Technologies’ rich heritage in delivering secure solutions to highly governed sectors, ensuring customers benefit from cutting-edge protection without compromising accessibility or flexibility. The organisation brings decades of experience from various sectors including defence, higher education and central government, which all demand the highest levels of security and compliance. This expertise underpins the SOC’s operational framework, which is built on rigorous industry standards, including ISO 27001 and Cyber Essentials Plus certifications. Looking ahead, Roc Technologies is poised to expand its SOC capabilities further. Over the next 12 to 24 months, the company plans to recruit additional cyber specialists, enhance its technological capabilities and deepen its integration with advanced tools such as artificial intelligence and automation.

Rubrik, Inc. announces the expansion of its pioneering cyber protection capabilities for cloud data that runs on AWS, designed to boost customers’ confidence and reduce the risk of downtime.  Rubrik’s upcoming expanded capabilities aim to accelerate cyber resilience for joint customers by expediting the identification of and the response to hidden threats, and by shortening the time to cyber recovery. Expanded features for AWS Central to the new services will be RCV, an isolated, air-gapped, and immutable backup repository Central to the new services will be Rubrik Cloud Vault (RCV), an isolated, air-gapped, and immutable backup repository that is fully managed by Rubrik. In addition, the company will provide expanded features for AWS that include Anomaly Detection, Threat Monitoring, Threat Hunting, and Data Discovery & Classification.  IT and security teams “Surviving a cyberattack is not as simple as just restoring from a backup. IT and security teams must also rapidly pinpoint when the attack occurred, identify what was compromised, and determine if sensitive data was impacted — all while trying to find a clean, safe recovery point,” said Anneka Gupta, Chief Product Officer at Rubrik. “This is no small task, but we believe the power of Rubrik and AWS makes it simple for organisations to bounce back quickly and safely while minimising the risk of reinfection. Together we will continue to bring our partnership to new heights to better protect organisations and join them on their journey to cyber resilience.” Key benefits of Rubrik Cloud Vault on AWS  To protect against bad actors gaining access to backup data that is wholly managed within an organisation, businesses often turn to an isolated data vault to ensure proper data protection. This introduces complexities when it comes to maintaining and securing the isolated environment, which can be a manual, time-consuming process prone to human error. Rubrik Cloud Vault on AWS will be designed to address this by offering a fully managed, isolated, off-site archive for backup data. Key benefits of Rubrik Cloud Vault on AWS will be designed to include: Immutable and isolated data protection: Maintain off-site, immutable data copies in an isolated environment to withstand cyber threats and always be able to recover clean data to your organization's preferred environment. Rubrik-managed security: Gain fully managed Rubrik capabilities to maintain security including immutability, role-based access controls, advanced encryption, quorum authorisation, and comprehensive monitoring. Rubrik extends advanced security features to AWS With Rubrik, joint customers in AWS will have access to deeper insights into their sensitive data and emerging cyber threats. This includes Anomaly Detection, which determines the scope of cyberattacks using machine learning to detect deletions, modifications, and encryptions for optimal ransomware investigation and accelerated recovery time. The new advanced capabilities aim to help customers recover faster and with greater confidence, ensuring restoration from a verified, clean point of recovery. These features will include: Threat Monitoring: Accelerates investigations and reduces the risk of malware reinfection during recovery by automatically analysing backup snapshots for threats using an up-to-date threat intelligence feed. Threat Hunting: Provides insights that help avoid malware reinfection during recovery by analysing the history of data for indicators of compromise to identify the initial point, scope, and time of infection. Data Discovery & Classification: Reduces sensitive data exposure and manages exfiltration risk by locating sensitive data in files and applications to help organisations stay compliant. Anomaly Detection is currently available to all AWS customers, with exciting developments planned for Threat Hunting, Threat Monitoring, Data Discovery & Classification, and Rubrik Cloud Vault in early 2025. Rubrik will showcase its innovation on-site at AWS re:Invent 2024 in Las Vegas. Attendees can visit booth #1948.

Alibaba Cloud, the digital technology and intelligence backbone of Alibaba Group, announced the launch of its revamped AI-focused partner ecosystem plan, known as “Alibaba Cloud Partner Rainforest Plan” during the Alibaba Cloud Partner Summit 2024 through a series of new initiatives, including an AI partner accelerator program, an enhanced incentive program and a revitalised global strategy for service partners. The initiatives aim to foster the growth of global partners and accelerate the development and deployment of cutting-edge artificial intelligence and cloud computing solutions for businesses across various industries worldwide. Benefits of the AI era “At Alibaba Cloud, we believe that collaboration is the key to unlocking innovation and driving growth. Our global partners are not just participants, they are the architects of a new digital landscape in the AI era,” Selina Yuan, President of International Business, Alibaba Cloud Intelligence said during the summit. “Today, with our revamped global partner ecosystem, we are committed to supporting our global partners to jointly reap the benefits of the AI era and meet the diverse business demand of global customers.” New AI-focused partner ecosystem initiatives  Initiative aims to enrich partner enablement and accelerate diverse partners’ digital transformation journey To meet the surging demand for AI technologies from global customers, Alibaba Cloud debuted the AI Alliance Accelerator Program to build a dedicated AI partner ecosystem through collaboration with 50 AI technology partners and 50 channel partners in 2025. This program offers selected AI technology partners enhanced technical support focused on AI, expanded distribution channels, collaborative go-to-market resources, and dedicated AI consulting services. Alibaba Cloud’s AI capabilities Meanwhile, chosen channel partners will benefit from increased financial incentives and market development funds for their AI-related initiatives. By leveraging Alibaba Cloud’s AI capabilities and its global technology ecosystem, the initiative aims to enhance partner enablement and accelerate diverse partners’ digital transformation journey. It also seeks to empower global partners to capitalise on the opportunities presented by the AI era, reaching a broader customer base through Alibaba Cloud’s extensive distribution network of channel partners Diverse digital transformation Alibaba Cloud has also unveiled an enhanced global system for its service partners Alibaba Cloud has also unveiled an enhanced global system for its service partners, introducing the Revitalised Service Partner Program. This initiative focuses on cultivating new service partners by upskilling channel partner and technology partners with targeted training and empowerment, equipping them with necessary capabilities of consulting, implementation and managed services to diversify their revenue stream and deliver a comprehensive service to the customer. It also seeks to empower existing service partners by expanding their offering to include both product reselling and service delivery. Additionally, leveraging Alibaba Cloud's Generative AI capabilities, the company has collaborated with service partners to jointly develop the Managed Large Language Model Service and other AI-focused services to foster an AI partner ecosystem and address the diverse digital transformation needs of global customers. Alibaba Cloud's new strategic partnerships Meanwhile, Alibaba Cloud pledged to extend new strategic partnerships with 18 service partners, including Whale Cloud, Bespin Global, Cognizant Worldwide, Deloitte, Accenture and FPT out of the existing 50 global standard service partners via enhanced resource sharing and capability complement, aiming to build a comprehensive service system that meets diverse needs of global customers.  In addition, the company also released its Synergistic Incentive Program, designed to strengthen the collaboration between its global technology partners and channel partners, fostering a vibrant and dynamic ecosystem. Alibaba Cloud’s extensive channel network Alibaba Cloud’s duty to empower its partners and nurture a robust global ecosystem The program introduces an expanded go-to-market pathway, enabling technology partners to boost revenue by leveraging Alibaba Cloud’s extensive channel network while channel partners gain access to a broader product portfolio, increasing sales opportunities and enhancing profit margins. This initiative drives mutual growth and reinforces Alibaba Cloud’s commitment to empowering its partners and nurturing a robust global ecosystem. Enhanced collaborations with global and regional partners  In order to support global customers to reap the benefit of digitalisation in the AI era. Alibaba Cloud has also announced an enhanced collaboration with innovative technology and channel partners, both globally and regionally, to provide cutting-edge cloud computing and AI products and solutions, fostering a thriving and sustainable ecosystem.

The National Cyber Security Centre (NCSC) new cyber chief, Richard Horne, has issued a stark warning about the growing complexity of “widely underestimated” cyber threats. Speaking at the launch of the NCSC’s eighth annual review, Richard Horne, Cyber Security Chief, commented: “What has struck me more forcefully than anything else since taking the helm at the NCSC is the clearly widening gap between the exposure and threat we face, and the defences that are in place to protect us.” Intensity of cyber-attacks Horne emphasised the frequency, sophistication, and intensity of cyber-attacks, which now target everything from healthcare to education, and has called for urgent collective action across public and private sectors to address these evolving threats. He stressed that the human cost of cyber-attacks is undeniable, and the UK’s reliance on technology has left it vulnerable to exploitation. Cost of cyber threats Horne highlighted the increasing frequency and sophistication of hostile cyber activity, particularly from state actors Horne highlighted the increasing frequency and sophistication of hostile cyber activity, particularly from state actors like Russia and China, who exploit the UK's technological dependency to disrupt and cause destruction.  He also pointed to recent cyber incidents, such as attacks on Synnovis and the British Library, which illustrate the human cost of cyber threats and the urgent need to enhance the resilience of critical infrastructure, supply chains, and the economy. UK's cyber risks Andy Ward, SVP International Absolute Security: "The NCSC highlights the alarming reality that the UK's cyber risks are growing faster than our ability to address them. This activity from state actors like Russia and China, combined with increasingly sophisticated cybercriminals leveraging AI, exposes critical vulnerabilities in our infrastructure, economy, and public services." "Alongside the NCSC warnings, our research shows that almost half (47 percent) of businesses have reported an increase in the volume of state-sponsored cyber threats over the past year. This reflects the urgent need for organisations to strengthen their defences against increasingly aggressive and sophisticated threats." Cyber resilience strategy Ward added: "The rise in incidents handled by the NCSC shows that these threats are not just hitting more frequently, but with greater severity. To address this, it is vital to implement a robust cyber resilience strategy." "This includes investing in prevention and recovery technologies to fortify defences, adopting incident response frameworks to reduce risks and minimise downtime, and enabling real-time visibility across all devices and applications so centralised IT teams can detect suspicious activity early." Digital health and security risk Matt Gibney, CTO of adCAPTCHA, commented: “Cyber and bot attacks are no longer a distant concern, they are a very real and growing threat that can target any organisation or individual." "With services becoming increasingly digitised, creating countless new entry points for cybercriminals, it's critical for businesses to conduct regular audits of their digital health and security risk to avoid falling victim to a costly breach." Cybersecurity audit Gibney added: "The NCSC highlights how the risks we face are widening faster than our defences can keep up, with cyber threats becoming more frequent, sophisticated, and impactful. A key part of these risks is the rise of bot networks. Once bots infiltrate IT systems, they can scrape and steal valuable data, sell monetised advertising space and content, and cause major financial losses." "This why monitoring for the presence of bot networks should be an essential part of any cybersecurity audit. Uncovering the full extent of bot issues allows organisations to prioritise investment in detection and prevention systems, ultimately strengthening their overall cyber resilience.” NCSC’s Annual Review The NCSC’s Annual Review highlights the rising use of artificial intelligence (AI) by cybercriminals, making attacks more efficient and harder to detect. Over the past year, the NCSC managed 430 cyber incidents, including a rise in data exfiltration and ransomware attacks, with sectors such as academia, manufacturing, and IT remaining highly vulnerable. The NCSC urges organisations to adopt stronger cybersecurity practices to mitigate these risks.

Rapid technological advancement, artificial intelligence (AI) and machine learning (ML) are revolutionising traditional on-premises video security systems. These next-level tools are not just enhancing video data capabilities; they're transforming how businesses approach security, operational efficiency, and information analysis. Video analytics have been a part of security systems for many years, but the arrival of deep learning in 2009 marked a turning point. By training neural networks, basic analytics tasks like motion detection, object detection, and tracking objects within scenes have become commonplace. This leap forward has paved the way for more sophisticated AI and ML applications in video security. Proactive security measures AI-powered systems can perform complex tasks such as pose estimation and anomaly detection Today's AI-powered systems can perform complex tasks such as pose estimation, anomaly detection, and behaviour analysis. These capabilities extend far beyond simple, passive monitoring, offering organisations rich insights and proactive security measures.  For instance, analytics can now determine whether people are engaged in hostile or benign interactions, recognise unusual events that may signal safety hazards, and even predict potential security breaches before they occur — all based on analysing massive amounts of data that humans alone could never process. Enhancing on-premises infrastructure While the power of AI and ML in video security is clear, integrating these technologies into existing on-premises systems presents both opportunities and challenges. One of the primary considerations is the increased demand for processing power and storage capacity. As solution technology expands, hardware requirements will increase. This reality necessitates a strategic approach to system design and implementation. Organisations must carefully evaluate their current infrastructure and plan for future needs to ensure their on-premises systems can handle the computational demands of AI and ML tools. However, the benefits often outweigh the challenges. AI-enhanced on-premises systems offer several advantages: Real-time processing: On-premises AI can analyse video feeds in real time, allowing for immediate response to security threats. Data privacy: Keeping data processing on-site can help organisations meet strict data privacy regulations and protect sensitive information. Customisation: On-premises systems allow for greater customisation of AI models to meet specific security needs. Reduced latency: Processing data locally eliminates the need for constant cloud communication, reducing latency in critical security applications. The role of open platform video technology To fully leverage AI and ML capabilities in on-premises video security systems, open-platform video management software (VMS) plays a crucial role. An open platform VMS allows for seamless integration of various AI and ML tools, cameras, and other security devices, creating a highly flexible and scalable system. An open VMS can integrate thousands of cameras and sensors, allowing for centralised management and analysis of vast amounts of data. This approach enables security teams to quickly adapt to new threats and implement new and unplanned AI and ML solutions as they become available. Video system management  The hybrid approach to video system management combines on-premises infrastructure with cloud services It's important to note that many organisations choose to deploy a hybrid approach to video system management that combines on-premises infrastructure with cloud services. This strategy can offer the best of both worlds: the control and low latency of on-premises systems with the scalability and advanced capabilities of cloud-based AI and ML tools. For example, some cities have implemented hybrid data storage models, hosting critical real-time data on local servers while leveraging cloud services for long-term storage and advanced analytics. This approach allows for efficient management of large amounts of high-resolution video data while reducing costs associated with on-premises storage expansion. Practical applications and benefits The integration of AI and ML into on-premises video security systems is transforming security practices across industries, offering benefits that extend beyond traditional surveillance. These advanced technologies enhance security measures while providing valuable insights for operational efficiency and strategic decision-making. By analysing video data in real time, AI and ML-powered systems can detect patterns and automate responses in unprecedented ways. Here are some key examples of sector-specific benefits: Retail: AI-powered analytics can optimise product placement, track shopping patterns, and enhance loss prevention efforts. Education: K-12 schools can use advanced video analysis to address issues like vaping and bullying, monitor traffic, ensure that proper procedures are followed, and provide enhanced safety and security. Manufacturing: AI can streamline quality control processes, detect safety violations, and optimise production line efficiency. Healthcare: Intelligent video systems can monitor patient safety, manage access control, and even assist in documenting and verifying that procedures and protocols are followed appropriately. Transportation: AI-enhanced video systems can improve traffic management, enhance security in transit hubs, and assist in incident response. Challenges and considerations Ensuring access to robust, diverse, and representative data sets is essential for training AI models effectively AI and ML hold great promise for on-premises video security, but organisations may encounter challenges during implementation. The considerable upfront costs could discourage smaller businesses or those with tight budgets. Nevertheless, this should be viewed as a long-term investment with significant returns in enhanced security and operational efficiency. Implementing AI-powered systems in video security can be complex, often requiring specialised skills, potentially creating a gap within existing IT or security teams. To bridge this skills gap, organisations may need to invest in training or partner with external experts to address this challenge. Additionally, the quality of data is crucial for effective AI and ML implementation; poor or insufficient data can result in inaccurate analyses and unreliable results. Ensuring access to robust, diverse, and representative data sets is essential for training AI models effectively. Benefits of integrating AI and ML Ethical considerations surrounding privacy, consent, and potential algorithmic bias are also critical. Organisations must strike a balance between enhancing security and safeguarding individual privacy rights to maintain public trust in these technologies. Despite these challenges, the benefits of integrating AI and ML into on-premises video security systems often outweigh the difficulties. Careful planning, resource investment, and a strong focus on ethical and regulatory compliance can lead to more effective, efficient, and intelligent security solutions. Future outlook Edge computing capabilities will enable sophisticated AI processing directly on cameras The future of AI and ML in on-premises video security promises significant advancements that will address current limitations and unlock new possibilities.  Edge computing capabilities will enable sophisticated AI processing directly on cameras and other security devices, reducing strain on central servers and potentially lowering hardware requirements. This, combined with more efficient AI algorithms, will democratise access to advanced AI and ML capabilities for organisations of all sizes. AI-powered analytics Predictive analytics will become a cornerstone of future video security systems, marking a shift from reactive to proactive security measures. As AI models become more sophisticated, their ability to anticipate and prevent security incidents will improve dramatically, revolutionising risk management and incident response.  The integration between video security and other business systems will deepen, with AI-powered analytics providing insights beyond security into business operations and strategic decision-making. Data for training AI models Explainable AI will become more overall, which is vital for building trust in automated systems Automation of security processes will reach new heights, freeing human operators to focus on high-level decision-making and complex situations. To support this evolution, we'll likely see increased use of synthetic data for training AI models, addressing privacy concerns, and improving model robustness. Explainable AI will become more prevalent, which is crucial for building trust in automated systems and meeting regulatory requirements. For security professionals, embracing these technologies is no longer optional but necessary to remain competitive and provide the best possible service to clients. By leveraging open platform VMS and carefully planning system architectures, organisations can create flexible, scalable, and powerful video security solutions that not only protect assets but also drive business value. Enhanced video security systems The key to success will be finding the right balance between on-premises control and cloud-based capabilities while addressing important considerations around privacy, ethics, and regulatory compliance. With thoughtful implementation and ongoing adaptation, AI and ML-enhanced video security systems will continue to play an increasingly central role in safeguarding our businesses, institutions, and communities.

As city managers, law enforcement agencies, and first responders face mounting pressure to combat crime and respond to emergencies with limited resources, real-time crime centres empowered by a new generation of data-driven technologies are emerging as an effective force multiplier.  Real-time crime centres Real-time crime centres (RTCCs) serve as centralised hubs where dedicated personnel leverage pioneering-edge technologies to analyse diverse data streams and provide critical support to law enforcement and emergency operations. These 24/7 facilities are transforming how agencies gather, process, and act upon information, enabling more proactive and efficient policing strategies.  The core functions of RTCCs  These centres provide officers with unprecedented situational awareness and real-time intelligence At their core, RTCCs are tasked with three primary objectives: enhancing safety, facilitating identification, and supporting apprehension. By integrating data from a wide range of data sources, these centres provide officers with unprecedented situational awareness and real-time intelligence.  Integrated data approach This integrated data approach allows RTCCs to alert officers to potential threats, quickly identify suspects, and guide responders during critical incidents. For instance, in the event of a robbery, RTCC operators can rapidly search camera and licence plate data to track suspect vehicles, significantly improving the chances of a swift arrest.  According to the Bureau of Justice Assistance at the U.S. Department of Justice, the mission of an RTCC is to centralise a broad range of current and evolving technologies, coordinate sworn and non-sworn human resources, and direct the attention to high-crime areas, active crimes in progress, high-profile or highly recidivistic offenders, and large-scale public events that may require law enforcement presence or response.  The technology powering RTCCs  The effectiveness of an RTCC hinges on its ability to seamlessly integrate a wide array of technologies: Open Platform Video Technology: At the heart of many crime centres is an open platform video management software (VMS) that serves as the central nervous system, unifying diverse data streams into a cohesive operational picture. By leveraging open APIs and SDKs, the VMS can incorporate a wide range of cameras, sensors, and analytics tools. This data-driven approach to video technology enables seamless alert distribution to both the RTCC and field officers via mobile applications.  IP Camera Networks: The eyes of an RTCC, these systems combine fixed, PTZ, multi-sensor, thermal, and other specialty cameras to provide continuous city monitoring. Strategically placed throughout urban areas, cameras offer comprehensive coverage of critical locations such as transportation hubs, commercial districts, and high-crime zones. This network forms the foundation for real-time monitoring and incident response.  Sensor Arrays: Beyond visual data, RTCCs employ various sensor technologies. Acoustic sensors can detect sounds such as gunshots, shouts for help, breaking glass, and other sounds instantly alerting officers and cueing nearby cameras. Environmental sensors monitor air quality for gasses, smoke, and other non-visible hazards.  Licence Plate Recognition (LPR): LPR systems act as a force multiplier, continuously scanning for vehicles of interest. By generating real-time alerts for stolen or wanted vehicles, these systems significantly enhance the ability to track suspects and recover stolen property, contributing to reduced auto theft rates.  Aerial Surveillance: Many RTCCs incorporate drone technology, providing on-demand aerial perspectives of developing situations. This capability is particularly valuable for monitoring large-scale events, assessing natural disasters, supporting operations in hard-to-reach areas, and serving as a powerful first response for crime scene situational awareness.  AI-Powered Analytics: At the heart of many RTCC operations are sophisticated AI algorithms that analyse video data in real-time. These systems can identify a range of suspicious activities, from unattended packages to unauthorised intrusions. By rapidly processing vast amounts of video data, they help operators focus on potential threats and anomalies.  Geospatial Mapping: To make sense of the influx of data, RTCCs rely on advanced mapping software. These tools visualise events, alerts, and data streams geographically, allowing operators to quickly identify patterns, clusters of activity, and relationships between incidents.  Database Integration: RTCCs maintain direct connections to various law enforcement databases, including local, state, and federal resources like the National Crime Information centre (NCIC). This integration allows for rapid background checks and threat assessments, providing crucial context for ongoing operations.  Cloud Infrastructure: The scalability and flexibility of cloud computing are revolutionising RTCC capabilities. Cloud and hybrid solutions offer secure, off-site storage and facilitate easy data sharing between agencies. This approach not only reduces initial costs but also allows for incremental upgrades, making advanced RTCC functionality accessible even to agencies with limited budgets.  Real-world impact  RTCC operators tracked shooting suspects via camera feeds, guiding officers to their location The proliferation of RTCCs across the United States with over 80 centres in operation speaks to their proven effectiveness. Cities that have implemented these high-tech command centres are reporting significant improvements in response times, clearance rates, and overall public safety.  Real-time surveillance In Winston-Salem, North Carolina, the local RTCC leverages over 1,300 live video feeds to provide real-time surveillance across the city. This extensive network, combined with gunshot detection technology and licence plate readers, has already demonstrated its value. In a recent incident, RTCC operators were able to track shooting suspects via camera feeds, guiding officers to their location for a quick apprehension.  Video analysis by RTCC Similarly, Newport News, Virginia, saw an immediate impact after launching its RTCC in 2021. The centre has played a crucial role in solving homicides caught on video and rapidly closing a series of carjacking cases.  These success stories underscore the game-changing potential of RTCCs when it comes to solving crimes and gathering evidence. In Memphis, Tennessee, video analysis by RTCC detectives helped identify a shooter in custody following an incident at a community basketball court even when no witnesses had come forward.  Identifying suspects with RTCC Officers and analysts can view street and body camera footage to monitor crowds at parades The Jackson Police Department in Mississippi has seen similar benefits since building an RTCC in 2019, part of a broader effort that included deploying 100 cameras and 271 body cams. Officers and analysts can view street and body camera footage to monitor crowds at parades and other events. During pursuits, the cameras provide extra surveillance, allowing officers to identify suspects or witnesses to help solve crimes.  Enhancing crime mitigation and emergency response  While RTCCs have proven their worth in responding to active incidents, their true potential lies in proactive crime prevention and enhanced emergency preparedness. By leveraging advanced analytics and integrated data sources, RTCCs are evolving into powerful predictive tools for law enforcement.  Pattern recognition algorithms For instance, pattern recognition algorithms can analyse historical crime data alongside real-time video feeds to identify potential hotspots for criminal activity. This allows law enforcement to strategically deploy resources, increasing visible presence in high-risk areas before crimes occur. Similarly, anomaly detection systems can alert RTCC operators to unusual behaviors or suspicious activities, enabling early intervention in potentially dangerous situations.  Asset and property protection, automated alerts RTCCs can monitor critical infrastructure, government buildings, and other high-value assets 24/7 Asset and property protection is another area where RTCCs excel. By integrating with access control systems and using AI-powered video analytics, RTCCs can monitor critical infrastructure, government buildings, and other high-value assets 24/7. Automated alerts for perimeter breaches, unauthorised access attempts, or suspicious objects left in restricted areas allow for an immediate response, significantly enhancing security postures.  Emergency response and preparedness In terms of emergency response and preparedness, RTCCs serve as vital command and coordination centres during crises. Whether facing natural disasters, major accidents, or other large-scale emergencies, RTCCs provide a centralised hub for information gathering and dissemination. Real-time video streams from affected areas, combined with data from environmental sensors and emergency service communications, allow for rapid situational assessment and coordinated response efforts.  Post-incident investigation and analysis RTCCs can also play an active role in post-incident investigation and analysis. The ability to quickly compile and analyse vast amounts of data from multiple sources can significantly accelerate case resolution and help identify patterns to prevent future incidents. As RTCCs continue to evolve, their capacity for integrating diverse data streams and leveraging advanced analytics positions them as indispensable tools in modern law enforcement strategy.   The future of technology-driven policing  The integration of artificial intelligence and machine learning promises to enhance video analytics As RTCCs continue to evolve, they are likely to incorporate even more advanced technologies. The integration of artificial intelligence and machine learning promises to enhance video analytics capabilities, enabling faster and more accurate threat detection. Additionally, the expanding use of drones, subject to FAA regulations, could provide RTCCs with cost-effective aerial surveillance options.  Effective and ethical operations However, the implementation of RTCCs is not without challenges. Agencies must navigate issues of privacy, data security, and community trust. Ongoing training for personnel and careful planning is essential to ensure these centres operate effectively and ethically.  Data-driven approach Despite these hurdles, the trend toward technology-driven policing shows no signs of slowing. RTCCs represent a shift from reactive to proactive law enforcement strategies, offering a data-driven approach to crime prevention and response. As these centres become more prevalent, they will play an increasingly vital role in helping agencies maximise their resources and make informed decisions, ultimately contributing to safer communities for all. 

Misconceptions about AI and analytics in video security are common due to the rapid evolution of the technology and varying levels of understanding. Artificial Intelligence (AI) and analytics are increasingly used as interchangeable terms when discussing video security cameras. AI v/s analytics While there is some overlap, it is important to articulate the differences between them when speaking to stakeholders or customers. As the myriad types of AI gain more prominence in the global dialogue and privacy concerns are increasingly raised, security professionals need to take extra care to educate executives and management in any organisation so that they can, in turn, represent the company's use of AI tools accurately. AI and analytics in video security Security cameras use subsets of AI, namely machine learning and deep learning, to recognise and classify objects The intent of this article is not to do an academic deep-dive on either AI or analytics, but instead to position each discipline as it relates to modern AI-based video security. The goal is to educate operations and management about the use of AI in video surveillance to support informed decision-making across the organisation. It’s worth mentioning that while AI is often used as a catch-all term, security cameras use subsets of AI, namely machine learning and deep learning, to recognise and classify objects.  Misconceptions Here are four common misconceptions about AI and analytics:  Misconception #1: AI and analytics are the same  People often confuse AI with analytics, but they're distinct. AI is used in the video industry to enhance analytics and analysis capabilities. The technique involves the use of the machine and deep learning algorithms to recognise or classify known objects like a person or vehicle. AI can further detect unique attributes of objects such as the colour of clothing, or additional objects that are carried or worn such as backpacks or glasses. Object detection  The processes overlap somewhat when AI is also used to enhance the analysis of complex behaviours Analytics, on the other hand, refers to the process of analysing what the detected object is doing. The processes overlap somewhat when AI is also used to enhance the analysis of complex behaviours. Is a vehicle traveling left or right in the camera’s field of view, possibly going the wrong way down a one-way street? Did it enter a restricted zone? Should a car arrive in this area at 3 a.m.? These are basic binary (yes/no) analytic tasks. Ascertaining whether two people are fighting or if someone is shoplifting is a more nuanced analysis that requires a sophisticated AI algorithm capable of considering multiple data points before alerting staff to suspicious behaviour.​ Addressing false positives with AI-assisted analytics ​Before AI-based object detection, analytics were prone to false positives any time the lighting changed (a passing cloud could change the pixels). Working together, AI and analytics have largely solved the issue of false positives for the objects they recognise. On a properly installed camera, AI-assisted analytics can issue proactive alerts or search through hours of footage for humans or vehicles with specific attributes incredibly quickly. AI adds classification and behaviour information to raise the overall accuracy of analytics and analysis. AI can also be used to enhance image quality in cameras, so there are many other ways it can be utilised.  Misconception #2:  AI can operate autonomously and replace security personnel  AI coupled with analytics can help operators monitor an increasingly larger number of cameras for anomalies and events While AI can enhance surveillance and response, the nuanced understanding and decision-making capabilities of humans are still crucial in most scenarios. AI coupled with analytics can help operators monitor an increasingly larger number of cameras for anomalies and events that may warrant attention, but the decision on how to act still firmly rests with the operator. This increasingly ‘intelligent’ assistant represented by AI helps security teams focus on what matters in an increasingly complex world, but it’s a team effort. And while AI’s capability to operate autonomously will surely improve, it’s hard to imagine a world in which it would be wise to let it make important decisions without human oversight.  Misconception #3: AI-based security cameras are invading the privacy Safeguarding personally identifiable information (PII) is a critical responsibility of any organisation. Because of the prevalence of data breaches, everyone is keenly aware of the risks of PII ending up in the wrong hands. For video security systems, it’s essential to realise that the descriptive metadata an AI-based camera captures is composed of anonymous data about the humans it detects.  Attributes such as the colour of clothing and whether a person is carrying a backpack or wearing a hat are certainly not sufficient to identify anyone personally. And while there may be grey areas with some AI systems that attempt to classify gender and age, they are still not identifying a specific person. Facial recognition Facial recognition is a specific, focused function, and while it might be improved with some AI-based techniques Most importantly, AI does not equal facial recognition. Facial recognition is a specific, focused function, and while it might be improved with some AI-based techniques, facial recognition has had its separate evolution distinct from AI. Facial recognition has privacy implications, while most AI implementations do not.  AI-based detection Additionally, AI-based detection of humans and vehicles typically happens “on the edge”, processed within the camera itself, while facial recognition almost always requires a separate VMS/server application and database to function. So, AI-based cameras don’t, by themselves, do facial recognition.  Misconception #4: AI can learn anything on its own  AI-based algorithms are only as good as the training they’ve received While AI can significantly enhance video surveillance capabilities, the machine and deep learning algorithms are not infallible. They require human oversight to manage false positives and interpret complex situations. AI-based algorithms are only as good as the training they’ve received. For example, human and vehicle detection algorithms have been carefully trained by R&D departments in laboratory settings with hundreds of thousands, if not millions, of representative images. This is why they can be very accurate when installed correctly. AI ‘on-site learning’ cameras For AI-based systems to truly learn to recognise something, they must also be informed when they get something wrong. This type of training usually occurs under the supervision of experienced AI developers. Recently, new AI ‘on-site learning’ cameras have become available. These can be trained by operators to recognise unique, customisable objects such as forklifts, shopping carts, airplanes, logos on vehicles, or any object an organisation might want to track or count. These systems must also be trained to be accurate. Intelligent training application AI on-site learning is also a great way to increase overall accuracy in any setting prone to false positives A typical on-site training challenge would be to capture an object in every lighting condition. To overcome this, forward-thinking vendors include an intelligent training application that automatically generates additional images across a range of luminance values, saving operators substantial time and effort while increasing accuracy. AI on-site learning is also a great way to increase overall accuracy in any setting prone to false positives.  Conclusion  Understanding these misconceptions is crucial for making informed decisions when implementing AI and analytics in video security systems and gaining consensus from stakeholders. As AI becomes ubiquitous across industries, it has the potential to lose its true meaning, particularly because we are only scratching the surface with machine and deep learning applications.  AI’s current capabilities and limitations Most importantly, we have to help educate all of our constituents that AI and analytics are not the same It’s also important to recognise that general (or strong) ‘AI’ does not yet exist. This is the ability of a machine to do any intellectual task a human can do. However, the marketing ship has long since sailed, so the best we can do is stay informed about AI’s current capabilities and limitations. Most importantly, we have to help educate all of our constituents that AI and analytics are not the same. AI does not equal facial recognition. Nor does it replace the need for human oversight. AI-based technology AI is a long way from non-structured, comprehensive learning and decision-making in a way humans would describe as ‘intelligent.’ With those caveats in place, the current AI-based technology functions as a fantastic assistant for security teams helping them to better protect people and property. 

Security applications for drones have evolved to provide benefits such as bird's-eye views of large areas, easy access to remote locations, and rapid deployment. However, to date, most drone applications have been outdoors. Not for long. Today, indoor drones are also finding unique opportunities for enhanced surveillance, security, and operational efficiency in indoor environments such as offices, warehouses, self-storage facilities, and malls. Indoor drones can navigate complex indoor spaces, providing real-time data and monitoring without the limitations of fixed cameras. New era of autonomous robotics A significant advantage of using drones indoors, as opposed to outdoors, is their ability to operate fully autonomously, circumventing U.S. Federal Aviation Administration (FAA) regulations that restrict such autonomy in outdoor environments. A new era of autonomous robotics enables drones to work seamlessly for users without the need for specialised flight training. A single security manager can oversee multiple indoor drones simultaneously with simple map clicks or prompts. A new era of autonomous robotics enables drones to work seamlessly for users Indoor monitoring and inspection Indoor Robotics is a company seeking to revolutionise indoor monitoring and inspection through its Control Bridge platform guiding indoor drones. Since its founding in 2018, Indoor Robotics has evolved through years of market engagement and product development. After initially recognising a demand for autonomous indoor monitoring, the company found that existing hardware fell short. “However, we understood the challenges of full autonomy and knew we would solve it using drones,” says Bar Biton, Marketing Manager of Indoor Robotics. Indoor Robotics has evolved through years of market engagement and product development Hardware challenges  Seven years later, with the hardware challenges addressed, the company is shifting focus to continually increasing value for security managers, especially with generative AI (artificial intelligence). In 2018, the problem was charging methods, which has been solved with ceiling docking stations and five patents. “Today it’s about making indoor environments safer and even saving lives by identifying blocked emergency exits, missing safety gear, leaks, fire hazards and more,” says Biton. While indoor navigation presents challenges—such as the unreliability of GPS and the need for precision — Indoor Robotics has dedicated significant resources to achieve centimeter-level accuracy and ensure the utmost safety, maintaining a record of zero safety incidents to date, says Biton. Indoor navigation presents challenges—such as the unreliability of GPS and the need for precision Advanced AI-driven navigation systems Navigation challenges for indoor drones include manoeuvering through confined spaces, avoiding obstacles, and maintaining stable flight in varied lighting conditions. To address these, Indoor Robotics employs advanced AI-driven navigation systems, real-time 3D mapping, and robust obstacle avoidance technologies. These solutions enable drones to adapt to dynamic environments, ensuring precise and safe navigation. Additionally, the Control Bridge platform provides real-time data and monitoring, allowing drones to adjust their routes and respond to changing conditions effectively, thus enhancing their operational reliability. Highly versatile indoor drones find applications across numerous vertical markets such as retail, logistics, healthcare, and corporate settings. Key use cases encompass security surveillance, where drones monitor premises continuously; maintenance checks, especially in hard-to-reach areas; safety inspections to comply with regulations and company policies; and emergency response to provide real-time data during incidents. In warehouses, drones efficiently inspect high shelves. Healthcare facilities and data centres use them to oversee restricted zones. Additionally, corporate offices employ drones to automate after-hours security, safety and maintenance routines. Indoor Robotics employs advanced AI-driven navigation systems, real-time 3D mapping, and robust obstacle-avoidance technologies Alerts to the remote management team One Indoor Robotics client, a global tech company, deploys drones to enhance site surveillance and operational efficiency across six offices in three countries. The drones conduct regular security patrols after-hours, monitor facility activities, and ensure compliance with safety standards. This deployment has significantly improved the overall safety and security of their offices. The drones provide real-time alerts to the remote management team, enabling prompt responses to any anomalies, such as maintenance issues or unauthorised access. “The key advantage is the unified security standard provided by our Control Bridge operating system, allowing them to oversee all their sites from one centralised platform, ensuring consistent security management across all locations,” says Biton. When indoor drones co-exist with human workers, primary challenges include ensuring safety and preventing disruptions. Drones are equipped with advanced sensors and AI-driven obstacle avoidance systems to detect and navigate effectively around people. Strict operational protocols and designated flight paths are implemented to minimise interactions. Additionally, many drone operations are scheduled for after-hours to further reduce potential disruptions. “Safety is our top priority, and we invest significant resources to ensure it,” says Biton. “We are proud to report zero safety issues to date, reflecting our commitment to maintaining a secure environment for both drones and human workers.” Deploys drones to enhance site surveillance and operational efficiency across six offices in three countries Implementation of indoor drones Indoor drones are significantly more cost-effective and affordable when compared to traditional security methods like additional cameras, sensors, manpower, and even ground robots, says Biton. They cover larger areas and provide dynamic surveillance in less time, offering real-time data collection and enhanced flexibility. Unlike cameras or ground robots, drones eliminate blind spots and adapt to environmental changes autonomously. They also offer substantial indirect savings by optimising maintenance routines, according to Indoor Robotics. For instance, a drone can instantly identify issues in hard-to-reach areas, allowing for immediate, targeted responses, instead of requiring an inspector first and then a technician, thus streamlining maintenance processes. “The biggest obstacle to greater implementation of indoor drones is education and awareness,” says Biton. “Many people are not yet exposed to the concept of autonomous indoor drones and may find it hard to believe they really work.” To overcome this, Indoor Robotics focuses on creating awareness and educating customers about the reliability and benefits of the technology. Demonstrations, case studies, and clear communication about the capabilities and safety of drones are key. By showcasing successful implementations and providing hands-on experiences, Indoor Robotics seeks to build trust and drive wider adoption of indoor drone technology in security applications. Control Bridge operating system Drones are designed with strict privacy controls and advanced AI to ensure they respect privacy norms A common misconception is that indoor drones are intrusive and pose significant privacy risks. However, drones are designed with strict privacy controls and advanced AI to ensure they respect privacy norms. They operate primarily during off-hours and are programmed to avoid sensitive areas, focusing solely on enhancing security and operational efficiency. The solution also includes rigorous data protection measures to safeguard any collected information, ensuring compliance with privacy regulations and addressing concerns effectively. Soon, automation will become integral to tasks across all facility types, from manufacturing and logistics to retail and office spaces. Using Indoor Robotics’ Control Bridge operating system, facility managers will deploy fleets of robots to identify issues, collect data, and gain insights to enhance operations, maintenance, and safety. Facilities will benefit from 24/7 AI-driven monitoring, eliminating the need for occasional surveys. Managers will receive immediate alerts for any anomalies, with preventive maintenance tasks seamlessly integrated into building management platforms, ensuring optimal performance and safety. New standards in the industry  The Indoor Robotics platform-agnostic approach provides flexibility and scalability. “As we continue to evolve, we support more and more platforms, enabling our clients to tailor their indoor monitoring solutions to their specific needs,” says Biton. “We believe that the future of security lies in intelligent, automated systems that can adapt to dynamic environments and provide real-time insights,” says Biton. Indoor Robotics seeks to be at the forefront of this transformation, setting new standards in the industry and paving the way for a safer, more efficient future.

The shift from standalone systems to fully integrated solutions is one of the biggest shifts the security industry has experienced in recent years.  There is a higher demand for integrated solutions that go beyond just security at the device and software level, and manufacturers have been continuously developing improved application programming interfaces (APIs), and hybrid and cloud-connected solutions.  Artificial intelligence (AI) Also, artificial intelligence (AI) plays an important role in modern intrusion systems by helping enable automated threat detection, real-time response, and predictive analysis. AI algorithms can analyse vast amounts of data to identify patterns and anomalies that may indicate security breaches. Security solutions are being developed with a focus on AI and machine learning to provide more proactive and resilient defences against increasingly sophisticated cyber threats. Benefits of AI AI-driven security solutions can continuously learn and adapt to new threats, providing more robust protection “The practical benefits of AI in security systems include enhanced accuracy in detecting threats, reduced response times through automation, and the capability to anticipate and prevent potential vulnerabilities before they are exploited,” says Sergio Castillejos, President, of Commercial Security at Honeywell. Additionally, AI-driven security solutions can continuously learn and adapt to new threats, providing businesses with more robust and dynamic protection. Unified Intelligent Command user interface Honeywell meets the challenge of better-integrated systems with a unified Intelligent Command user interface (UI). Castillejos says Honeywell continually innovates with the latest analytics and encryption to keep up with evolving threats. Honeywell’s products integrate with many offerings for partners to construct a robust and modern system relevant to their security needs.  Advanced cloud-based security Advanced cloud-based security technologies have been developed that offer real-time monitoring, automated threat detection Advanced cloud-based security technologies have been developed that offer real-time monitoring, automated threat detection, and remote management, essential for hybrid work environments, says Castillejos. “These solutions enhance scalability, improve data analytics capabilities, and provide seamless updates reducing significant maintenance costs that help companies to respond swiftly to emerging threats and enable robust, adaptive security measures.” Physical and digital security The best security systems are a combination of physical, digital, and national security, says Castillejos. While Honeywell focuses on providing the best in physical and digital security within their solutions, protecting sensitive and/or personal information must also be within the responsibility of the organisational policy.   Cybersecurity for connected devices Some of the challenges in the next five years will likely include integrating advanced technologies Security systems can safeguard this information by being highly configurable while also notifying users of unwanted activity. Sometimes, just restricting access to sensitive areas can be enough. However, in the world of data analysis and machine learning, security systems can audit and report on users who have accessed data to ensure that the protections are in place. Some of the challenges in the next five years will likely include integrating advanced technologies such as AI and the Internet of Things (IoT) while securing cybersecurity for connected devices, notes Castillejos.  Balancing act “Additionally, there will be a growing need for skilled professionals to manage and maintain these complex, connected systems,” he says. “Balancing cost-effectiveness with the demand for resilient security solutions will also pose a significant challenge, especially for smaller businesses.” Legacy systems that are susceptible to vulnerabilities like cloning or unauthorised access present the largest challenge to overcome. “However, as technology evolves, it becomes more challenging for a customer to manage a unified security system rather than a collection of unique solutions that all operate independently,” says Castillejos. Disruptive technology But investing in the newest analytics, AI and IoT will not improve a company’s physical security systems if they do nothing with the data. “They are not a replacement for the devices that keep people and property safe,” says Castillejos. “They can enhance a user’s experience and speed up the time to respond when they are planned correctly.”  The best security systems will look at disruptive technology as another tool in the overall system. However, the focus should remain on the user experience. If the latest technology is not properly integrated or configured, it will turn into more noise that most operators will ignore. {##Poll1720586145 - Which is the most useful benefit of artificial intelligence (AI) in security systems?##}

Security professionals are recognising the intelligence value of leveraging publicly and commercially available information. This information can now be accessed more effectively from typically hard-to-reach regions. Also, the technological capabilities have matured in our age of artificial intelligence, machine learning, and data science. Intelligence has historically been based on classified data. However, today’s unclassified data, including open-source intelligence (OSINT), is increasingly being used to provide context and queuing for other types of intelligence. Advanced identity intelligence Babel Street is a technology company providing advanced identity intelligence and risk operations using an AI-enabled data-to-knowledge platform to unlock insights from a flood of data. The company provides advanced data analytics and intelligence for the world’s most trusted government and commercial organisations. Experts have predicted that by 2025 over 463 exabytes of data will be generated each day globally The sheer volume of data is growing exponentially. Experts have predicted that by 2025 over 463 exabytes of data will be generated each day globally. Not only are we seeing exponential growth in the volume of data, but there is also disparity in the veracity and the variety of data. This is being compounded by the ‘app economy’ in which data is created in a new format for every app added around the globe. Human language technology “The problem is that the data ‘junk’ and the ‘crown jewels’ are in the same bucket, and government and commercial entities need better and faster ways to extract intelligence from these torrents of data,” says Farid Moussa, VP, Strategy & Public Sector, Babel Street. Prior to joining Babel Street, Farid retired from the National Security Agency (NSA). He has guided video, image, speech, and text analytics (VISTA) and developed an appreciation for human language technology. An elusive source of data is the Dark Web, where every user, by design, is attempting to obfuscate their identity, and bad actors are hiding much better. “This presents a cat and mouse game – the cat must be smarter than the mouse, but the mouse is continually getting smarter,” says Moussa. Intelligence tools for data analysis SIGINT and HUMINT – while both vital – are also the most expensive forms of intelligence There are several intelligence tools for analysing data. One of them is signals intelligence (SIGINT), which refers to electronic transmissions collected by ships, planes, ground sites, or satellites. Another is human intelligence (HUMINT), which is collected in a human-to-human fashion. Open-source intelligence (OSINT) is obtained by searching on topics or entities of interest that are publicly available on the Internet at large. Today, these various categories are often done in ‘silos of excellence.’  However, the best practice is using all forms together in a holistic fashion. SIGINT and HUMINT – while both vital – are also the most expensive forms of intelligence, while OSINT, which is growing in importance, is most cost-effective. All are vital forms of intelligence; OSINT is complementary and crucial to holistic intelligence practices. Holistic intelligence practices When it comes to physical security of people and places, OSINT has become a critical source of actionable information. Security directors leverage Publicly Available Information (PAI) to safeguard against threats to individuals, property, travel routes, and event sites. By monitoring PAI, security teams can detect and respond to potential dangers, including during and after events where thorough preparation is vital. Online information can contain warning signs of impending threats. It informs security professionals in uncovering digital traces, confirming intentions, and addressing risks across language barriers, ensuring proactive risk management for the protection of people and property. Role of Natural Language Processing (NLP) The Internet and social media were mostly English language by default, but that has changed exponentially Natural Language Processing (NLP) is a crucial capability that has evolved to recognise the richness and variety of words and names in multiple languages and scripts, and their use across cultures. Using machine learning and linguistics algorithms, the technology simultaneously considers numerous types of name variations. At one time, the Internet and social media were mostly English language by default, but that has changed exponentially.  Babel Street’s world-class entity matching technology measures over 100 features to calculate the similarity of entities across multiple languages. Despite advances in data management and the cloud, there are still multiple challenges and complexities with integration of these data elements. Challenges include spelling variances/phonetics, language translation issues, criminal evasion, human error upon input, typos, etc. Accessing data from a scattered landscape While there have been advancements in cloud technologies, agencies utilising open-source data are typically working within a highly scattered data landscape and must use a wide array of tools to get at the relevant pieces. This fragmentation makes it difficult to run analytics and apply AI and machine learning at scale in order to derive actionable insights.  Unstructured and relationship data are visualised through advanced link analysis As with many disciplines, artificial intelligence (AI) is changing the game when it comes to intelligence. NLP and AI algorithms are employed to enhance datasets for greater quality, usability, and completeness. Unstructured and relationship data are visualised through advanced link analysis, geographic heat maps, influential entity carousels, topic clouds, and patterns by time and day. Geographic heat maps The advanced algorithms accurately score and prioritise critical entities within the relationship network while providing the citations from which an AI/ML-based decision was made. “With the democratisation of AI, the world is becoming flat,” says Moussa. “Just like the most prosperous countries, even the poorest countries have the most advanced capabilities to do damage. Third-world economies often present a scenario where the financial gain of nefarious schemes and low-to-no regulation combine to incentivise bad actors.” The Challenges of Name Matching Identity has been an ongoing challenge for intelligence analysis due to the vast complexity of linguistics, spelling and cultural variances, human error, as well as human evasion. Technology and data science approaches are maturing, however machine translation can still struggle with meaning. The best-of-breed natural language processing capabilities run against the data while it still is in its native language. This minimises the occurrence of analytic errors caused by inaccurate machine translations. This minimises the occurrence of analytic errors caused by inaccurate machine translations It’s tempting to think that name matching is like doing a keyword search. The complexity of language makes it more challenging. New names are constantly created, with multiple spellings and no set of rules to encompass how names are formed. They are variable across languages, scripts, cultures, and ethnicities. Culturally specific nicknames and aliases add to the complexity. Replacing human involvement The investigation of the Boston Marathon Bombing in 2013 spotlighted an example of the significance of intelligence analysis. Even though the FBI had issued a detain alert for Tamerlan Tsarnaev back in 2011, Tsarnaev managed to travel to Russia in January 2012; and in July 2012, he returned to Boston. He was not detained on either occasion because there were too many names on the lists, and Tsarnaev’s last name had been spelled differently from the way it was on travel documents, thus enabling him to get through security. With the Internet, social media, and the dark web, there’s been an exponential increase in public communications in various languages, adding significantly to the amount of analysis required to keep societies safe. Name matching, using AI, analyses multiple contextual data points across languages to arrive at matches. Name matching, using AI, analyzes multiple contextual data points across languages to arrive at matches A common misconception is that this technology will replace human intelligence. “It’s more accurate to recognise its role as a force-multiplier, allowing humans to focus on the on the harder problems and/or vetting the results of AI,” says Moussa. “The technology can efficiently analyse massive volumes of data and distill it into actionable information in a timely manner. It augments human capabilities, enabling analysis at speed and scale beyond human capacity, without replacing human involvement.” Commercial Technology to the rescue “When it comes to threat and identity intelligence, we face a risk-confidence gap, underscored by the challenge of integrating traditional tactics with the modern digital landscape,” adds Moussa. “We cannot ‘hire’ our way out of this problem. Instead, it is imperative that we adopt technology to scale our efforts and free humans to solve the harder problems that machines cannot solve yet.” The public sector loves to build things, but there are time-to-value and return-on-investment considerations to the ‘build or buy’ decision. When commercial technology can be leveraged by government, it frees resources up to work on problems that the commercial world hasn’t yet figured out, says Moussa. “The public and private sectors need to come together – one team, one nation, working together with mutual trust and collaboration,” he says.

Reliable identity verification is an unwavering requirement at mission-critical checkpoints such as border crossings. Oftentimes, however, this involves slow manual processes that create a ripple effect of inefficiency and security risks. Passengers endure long wait times leading to frustration, fatigue and dissatisfaction. Indonesia Immigration recognised this strain on travellers moving through its destinations — specifically in one of the region’s busiest locations: the international seaport at Batam Centre. Batam Centre is one of the most-trafficked border spots between Indonesia, Singapore and Malaysia. Approximately 500,000 people move across Batam’s five seaports each year. The challenge Extremely long wait queues for international departures and arrivals were a severe pain point for the port Extremely long wait queues for international departures and arrivals were a severe pain point for the port. The root cause was the outdated manual process of handling identity verification for the tremendous number of passengers moving through the centre. People had to present their documentation papers and wait to be reviewed and verified before crossing the border. Officials sought an intuitive, contactless solution to automate border control, process passengers faster and improve the traveller experience. They also required a system with strong security measures and high performance in challenging lighting to accommodate varying traffic control and conditions. The solution Facial recognition is becoming an increasingly important tool for border security. It is fast, seamless and secure, and offers a contactless approach for identity verification. Working through Indonesia Immigration’s local system integration partner, the HID U.ARE.U™ Camera Identification System was selected as the facial recognition component for the automated border crossing (ABC) gate — or Autogate per Indonesia Immigration — installed throughout the Batam ports. Combining a self-service gate system, document reader and facial recognition camera immediately transforms border control and boosts the passenger experience. HID U.ARE.U™ Camera is an edge-computing device, delivering unsurpassed face detection, authentication & verification This intuitive passenger verification begins when an individual approaches the Autogate and places their passport on the HID ATOM™ document reader to scan the data. Once confirmed, the first gate opens, and the traveller steps forward in front of the HID U.ARE.U™ camera to scan their face. Once the system confirms a match between the passport photo and the passenger’s face, a second gate opens, and the visitor is on their way — all within seconds. HID U.ARE.U™ camera The HID U.ARE.U™ camera stands out as an edge-computing device, delivering unsurpassed face detection, matching, identification and verification directly at the edge. The camera was selected based on its engineering excellence that met the project’s many requirements, including: Combined HID-patented multispectral imaging (MSI) technology with artificial intelligence (AI) to deliver impeccable performance — even in challenging lighting conditions On-device biometric processing — face detection, capture, image quality checks and liveness detection — for the highest level of performance and maximum data protection Industry-renowned presentation attack detection (PAD) with passive liveness detection to prevent fraud attempts in unattended use cases (ISO 30107-3 PAD Level 1 compliance, Level 2 pending) Top NIST ranking in matching speed and accuracy Ethically trained and built AI to reduce matching bias Results People passing through the Batam Centre ports engage with top-notch facial recognition technology to quickly, seamlessly and securely authenticate themselves. The Autogate system helps increase efficiency, shorten passenger wait times and enhance the traveller experience. The entire identity verification process is now accomplished in seconds, greatly improving passenger throughput and operational efficiencies. Benefits of HID U.ARE.U™ Camera Identification System. “People moving through borders really appreciate the efficiency provided by this Autogate system with facial recognition,” said Silmy Karim, Director General of Immigration in Indonesia, adding “Wait queues are now drastically decreased and passengers are empowered by the fast and convenient self-service process that has them on their way in a matter of seconds.” Key benefits realised by Indonesia Immigration: Shorter wait times at the checkpoints Improved passenger experience Increased operational efficiency Enhanced border security

Indexable inserts are interchangeable cutting tools that are indispensable in various industrial applications, especially in metalworking. They are used as cutting material carriers for machining metals, plastics or wood. Their manufacture requires high-precision production processes to ensure an exact geometry and perfect surface finish. Even minimal deviations affect not only the service life but also the performance of the cutting insert. The smallest defects that are invisible to the human eye can cause immense damage, for example when milling or cutting high-quality components - including consequential costs. Careful quality control is essential to ensure that only flawless indexable inserts leave the production process and meet the high requirements in terms of durability and reliability. A flagship project by automation and measurement technology specialist Xactools from Germany demonstrates how artificial intelligence can help visual inspection make quantum leaps. The German medium-sized company has developed a fully automated handling and inspection system for a global manufacturer of indexable inserts based in Scandinavia, in which the DENKnet solution for AI-based image evaluation plays a decisive role and sets new standards in terms of performance, zero-defect production and speed. Application Edges of the indexable inserts are rounded and ground, and their covers are blasted, ground and coated Around 1.2 million indexable inserts leave the Scandinavian company's production halls every week, which have to guarantee the highest possible process reliability and maximum productivity in the metalworking, automotive and aerospace industries, for example. They are manufactured using the sintering process, in which powdered metals, hard metals and other materials are pressed into the desired shape and then sintered, i.e., bonded together under heat and pressure. The strong and robust structure created in this way makes it possible to combine materials with different properties in order to achieve the desired cutting and wear resistance properties. After the sintering process, the edges of the indexable inserts are rounded and ground, and their surfaces are blasted, ground and coated. The Robotvision system from the Swabian engineers is used directly after the second manufacturing step, the sintering process. "The earlier defects are detected in the process, the better and cheaper it is to rectify them," says Marvin Krebs, Director Technical Sales at Xactools, explaining the system's position. A total of eight high-resolution industrial cameras and two spider robots are used to handle and inspect the indexable inserts for defects, which keep an eye on and load three rotary table nests and finally one pin pallet each. DENKnet's AI forms the heart of the complex image processing system between cameras, robots and a multi-GPU computing rack. Requirements The AI-based image evaluation software used had to be trained to correctly recognise As versatile as the areas of application of the small tool parts are, so varied are their properties and geometries. This manufacturer alone has around 2,800 products in its portfolio, which can be divided into almost one hundred geometry families. The aim was to automate handling and defect inspection for all of these. "The first challenge results from the numerous colour variations within the powder per pressing process," explains Marvin Krebs. "If certain parameters such as time, pressure or positioning vary, this leads to colour or gloss level deviations or to a different distribution of speckles on the surface, but this is not a defect." The AI-based image evaluation software used had to be trained to correctly recognise the numerous possible colour deviations of the surfaces and rate them as "OK". On the other hand, the smallest irregularities such as cracks, scratches, inclusions or other anomalies must be recognised as such and classified as "NOK". The inspection of metal surfaces is considered one of the highest skills of surface inspection, as their texture can be matt, shiny or even reflective. "The AI had to be extremely trained to variations and lighting conditions for this application," emphasises Marvin Krebs. AI results for the metal components The customer himself trained the customised image analysis solution with the DENK VISION AI Hub But in addition to the visual appearance, it is also about the insert geometry. Categories such as triangle, rectangle, rhombus or square can be found in countless variations due to the smallest deviations and are therefore divided into manageable subcategories, so-called geometry families. Xactools made the pre-selection for the training of the meshes; almost one hundred geometry families were defined and then taught in by the manufacturer itself. What sounds like a laborious undertaking was done surprisingly quickly.  "No more than 20 to 30 images were needed to teach each geometry family," recalls Marvin Krebs. The DENKnet palletising AI used for this purpose uses the DENKnet segmentation and classification network. The customer himself trained the customised image analysis solution with the DENK VISION AI Hub. The AI was integrated into the production line in just a few months and achieved almost perfectly reliable AI results for the metal components to be tested right from the start. "Indexable inserts identified as defective are sorted out and grouped according to the size and position of the defect. The AI image analysis detects more than 99 percent of production errors," adds Daniel Routschka, Sales Manager Artificial Intelligence at IDS Imaging Development Systems GmbH. But how exactly does the system work? A lighting screen measuring 1 x 1 metre provides extremely high illumination at the palletising stations A total of eight cameras with resolutions between 5 and 30 megapixels provide live images of the indexable inserts, which are positioned by magnetic or interchangeable grippers. For example, a camera records the individual indexable inserts from below and from above in order to check them for surface defects. Two other cameras check their cutting edge.  A lighting screen measuring 1 x 1 meter provides extremely high illumination at the palletising stations. "The system detects defects in the thousandth of a millimetre range," emphasises Marvin Krebs. This ensures that no damage is caused to the high-end surfaces to be processed later. This is because "uneven and faulty milling processes can potentially impair profitability and competitiveness", as the manufacturer also knows. To prevent this from happening during the production process and to exercise the greatest possible caution, the system also records images of the contour and position of the panels after inspecting the surfaces and edges. New versions of indexable inserts The contour of the insert and the outer edge of the gripper are detected in order to correct the position It can see exactly where and in which rotational position the indexable insert is positioned so that the magnetic gripper can finally place it on pin pallets. To ensure this, the gripper, to which the indexable insert is attached, moves over a camera that detects the exact position of the hole from below. At the same time, the contour of the insert and the outer edge of the gripper are detected in order to correct the position of the indexable insert and hit the pin if necessary. In addition, each individual pin position is detected in order to recognise bent and broken pins so that they are not palletised in the first place. "The system has been running for six months and the self-learning, global AI now recognises parts that it has never seen before. After just three to four months, new versions of indexable inserts no longer had to be trained for inspection. The underlying geometry is no longer relevant for the AI; it knows the contour and can also differentiate between IO and NIO for new parts," explains Marvin Krebs. High-performance AI image analysis with 99% picking efficiency The image analysis of live images from eight cameras via a DLL requires enormous computing power For Marvin Krebs, the added value of the DENKnet system compared to conventional image processing is obvious: "Without AI, the creation of part families and defect detection would be completely unthinkable. With rule-based image processing, the robot would also recognise parts within the standard range as NOK and sort them out." In addition, thanks to the Vision AI Hub, no hard coding is necessary, and the flexibility of the networks was another selection criterion for the intelligent DENKnet software. "We were able to easily embed the DENKnet palletising AI and several object classes for defects into our own Xactools image processing software via an API," says Marvin Krebs. However, the performance of the solution is almost unique. The entire inspection process takes place in a cycle time of four seconds, with almost 100% picking efficiency. The image analysis of live images from eight cameras via a DLL (Dynamic Link Library) requires enormous computing power. "We work with DENKnet for a good reason. The performance is not comparable with that of other providers, it is truly excellent," emphasises Marvin Krebs. "Using artificial intelligence in the most diverse variants on this scale has never been done before." Further variations are currently being tested, for example, to further simplify hole detection. Outlook The extremely varied surfaces and geometries as well as intolerances in the thousandths of a millimetre range make the visual inspection of indexable inserts a supreme discipline that can be transferred to many other demanding applications. The self-explanatory training environment DENKnet serves as an incomparably simple and at the same time high-performance tool, because it can be operated without programming knowledge and enables the automated training of AI with just a few clicks. A wide range of Vision AI technologies are available for this purpose. "This solution can be customised to any use case and there are no limits - no matter how many “classes”, which camera technology, how large or small the images or even how mixed the data sets are in terms of resolution and type, for example," adds Daniel Routschka, Sales Manager Artificial Intelligence from IDS. "Over 95 percent of our measuring and testing systems have at least one AI object class integrated. The potential areas of application are getting bigger and bigger for us, the market is growing," confirms Marvin Krebs. Promising prospects for this exemplary automated AI training for the highest demands.

Liberty Defense Holdings Ltd., a pioneering provider of next-generation, Artificial Intelligence (AI) based technologies for the detection of concealed weapons and other threats, is pleased to announce that its HEXWAVE™ system has been purchased by a major international airport in New York to support its aviation worker security screening program. “We are thrilled to have received the award following a public tender and to be chosen to support the airport's aviation worker screening requirements,” said Bill Frain, CEO of Liberty Defense. “The flexibility and comprehensive detection capability that HEXWAVE offers are driving widespread interest in the system from across the aviation sector. It is highly portable and can be rapidly deployed both indoors and outdoors to seamlessly facilitate screening in various areas of the airport." Physical screening procedures In April 2023, the Transportation Security Administration (TSA) issued an Airport Security Program National Amendment, which will require U.S. airports to adopt physical screening procedures for employees with access to secure-side areas. HEXWAVE enables rapid, automated, high-throughput screening using a contactless, walkthrough portal that can detect a diverse range of threats well beyond what enhanced metal detectors on the market can detect. It uses millimetre wave, advanced 3D imaging, and AI to detect all types of concealed threats, including both metal and non-metal items, liquids, powders, plastic explosives, 3D-printed ghost guns, and other novel threats or prohibited items – without the passenger having to divest common items like keys, wallets, or phones.

Creating a calm learning environment where all children feel safe is a challenge for secondary schools, and for new students, in particular, they can be an intimidating place. Badly behaved pupils can disrupt others and sometimes will damage school property. Advanced detection devices, can tackle anti-social behaviour and problems associated with increasing numbers of students that are vaping. By installing a smart sensor schools can ensure that staff time is not consumed by a minority of troublemakers. These can be placed discreetly in private areas, such as school toilets and changing rooms, that would be unsuitable for video camera surveillance. Aggression detection feature Schools have found that the increasing number of students vaping within its toilets becomes a difficult issue to manage and is often associated with anti-social behaviour but monitoring can help. An aggression detection feature allows for the monitoring of anti-social behaviour. By applying machine learning a smart device can learn what the normal sound levels are and alerts when a threshold above normal is detected for a specified length of time.  An aggression detection feature allows for the monitoring of anti-social behaviour The device can then pick up when a number of children have gathered together, students shouting, signs of fighting or pupils potentially being bullied by others. An alert will be sent by email to designated staff when abnormal noise levels are detected and action can be taken quickly. This means that perpetrators of aggression against other students or those vandalising school property within toilets can be stopped and dealt with as soon as an incident occurs. Being able to do this should act as a deterrent but also mean that repeat offenders can be dealt with more effectively by the school. Most advanced monitoring devices Security and monitoring firm has been aiding schools in Worcestershire and elsewhere Security and monitoring company, Ecl-ips, has been helping schools in Worcestershire and elsewhere, by supplying one of the most advanced monitoring devices, the HALO Smart Sensor. John Speller, Facilities Manager at Hanley Castle High School, near Malvern, reported that after installing the monitoring devices, “We have really cracked down on antisocial behaviour in our toilet blocks.” Matthew Carpenter, principal at Baxter College in Kidderminster, said: “It has transformed the amount of antisocial behaviour in toilets, children are more confident in going to the toilets. It has also reduced the number of students asking to go to the toilet during lessons.” Vapes laced with THC Meanwhile, there have also been concerns by schools about vapes laced with THC, with some Burnley school children reportedly hospitalised last year. The HALO is the only vape detector on the market that can alert and differentiate between vaping, vaping with THC and intentionally masking vaping behaviour, for example, by using aerosols to cover up vaping. Charlotte Slattery, Deputy Head Teacher at St Joseph’s College in Stoke-on-Trent, said she would recommend the HALO Smart Sensor to: “Any schools who are struggling to get on top of vaping in schools, or indeed aggression, in the toilets.”

Cequence announced that the world's largest navigation device manufacturer has chosen the Cequence bot detection and mitigation solution API Spartan, part of the overall Unified API Protection (UAP) platform, to secure its e-commerce experience and deliver a frictionless shopping experience for its customers. The company joins an already elite roster of clients, standing alongside industry giants spanning diverse sectors such as beauty, retail, government, telecommunications, systems integration, international voice traffic carriers, online automotive, motorcycle enthusiasts, and marine classifieds. Boosting online security As the company aimed to boost online security, it faced alarming numbers: about 100 million SSO login requests monthly, with 15 to 20 percent flagged as malicious. They also uncovered significant financial risks, with account takeovers costing anywhere from $50 (£40) to $12,000 (£9,500) each. Ignoring these unsettling numbers might have spelled financial disaster for the business, potentially surpassing the billion-dollar mark. Lack of behavioural analysis The previous solution relied solely on identifying bots based on bad IP addresses, which proved inadequate In light of the company’s previous experience with a prominent internet security provider that utilised rudimentary bot protection methods, it became evident that their efficacy in stopping malicious bots was compromised. The previous solution relied solely on identifying bots based on bad IP addresses, which proved inadequate in detecting many sophisticated malicious bots due to the lack of behavioural analysis. Consequently, the navigation device manufacturer faced challenges in effectively mitigating bot attacks and ensuring business continuity and customer experience. Cequence API Spartan Recognising the limitations of their existing bot protection measures, the customer sought a more proactive and comprehensive bot management solution like Cequence API Spartan to safeguard their business continuity, protect their online assets, and enhance the overall customer experience. Cequence's ability to distinguish genuine users from bots in real-time and adapt to evolving bot tactics resonated with the company, offering a reliable and future-proof solution to their bot problem. Proactive and comprehensive bot management "Bots aren't just a technical nuisance; they're customer experience assassins,” said Ameya Talwalkar, CEO of Cequence. “Imagine loyal customers, eager to purchase your products, locked out by an army of automated bad actors." "The frustration, lost sales, and reputational damage are a nightmare scenario no business can afford. That's why Cequence is dedicated to providing solutions that go beyond simple bot detection. We empower companies to proactively safeguard their legitimate customers and foster a thriving online environment where trust and genuine interactions flourish." Vulnerability due to automated bot attacks The OWASP API Security Top 10 highlights the vulnerability of poorly secured APIs to automated bot attacks. This blurs the line between traditional API and bot attacks, requiring unified security solutions that address both. Key features of Cequence API Spartan As the only API security solution with bot management capabilities, Cequence provides the navigation device manufacturer with: Continuous Behaviour-based API Threat Detection: Cequence leverages the behavioural fingerprint created by a machine learning-based analytics engine to track sophisticated attacks continuously. Supported by the largest API threat database in the world, with millions of behavioural and malicious infrastructure records, the analysis results are translated into policies and models that can be implemented on day one for high-efficacy protection. Integrated Security Ecosystem: While Cequence offers native real-time attack mitigation capabilities, it seamlessly integrates with existing security solutions such as web application firewalls (WAFs). This collaborative approach ensures holistic protection, allowing organisations to leverage the strengths of multiple security tools for enhanced API security and threat mitigation. Protection in Minutes: Cequence can be enabled to protect your APIs and web applications in as little as 15 minutes and can immediately begin reducing the operational burden associated with preventing attacks that can result in fraud, data loss, and business disruption. Advanced AI and machine learning The current e-commerce environment is increasingly vulnerable to bots exploiting loopholes in business logic. Cequence offers a robust solution to protect web and mobile applications, as well as their underlying API infrastructure, from business logic abuse. Leveraging advanced AI and machine learning, Cequence analyses incoming traffic to effectively identify and thwart even subtle attempts at exploitation.

The North Syracuse Central School District (NSCSD), a K-12 public school district in Central New York state, serves the communities of North Syracuse, Clay, Cicero, Bridgeport, and Mattydale. With 11 elementary, middle, and high schools, the district covers almost 90 square miles and has 7,792 students and approximately 700 teachers. With some of its school buildings over 60 years old, the district needed to renovate many of them, some more urgently than others. As part of the process, district administrators and staff re-evaluated all infrastructure elements and their approach to campus safety, selecting AtlasIED IPX technology to modernise their intercom, audio announcements, and emergency communications systems. Audio communications technologies Schools in the district used alike audio communications technologies had been in use for 10-20 years The district began renovating in phases, prioritising schools based on the state of the school buildings and the level of urgency of repairs. Before renovations, the schools in the district used similar audio communications technologies that had been in use for 10-20 years, including the public address (PA) system, clocks, and blue light systems for emergencies. However, the systems were siloed and did not integrate. During routine use, such as all-school announcements at the beginning of school days, the system functioned as needed, but during drills, the number of systems in operation caused the school's challenges. "With the old system, when we conducted a lockdown drill, school staff needed to activate the different systems manually, which created steps and more possibilities for human error," said Matt Erwin, Director of Facilities for North Syracuse Central Schools. Erwin manages maintenance and operations, plus security, health, and safety, and the capital work for the district.  AtlasIED's IPX Series features The district had two primary goals when upgrading the campus audio and communications systems: to improve the audio quality and find a plan to increase the speed at which a school could react and contact first responders during an emergency. They wanted to achieve these goals without having to install a system that was too complicated for staff and personnel. Because the district used a Cisco phone system, Erwin and his team wanted a platform that integrated with these devices. AtlasIED's IPX Series features a range of communication endpoints that interconnect As they researched and discussed options, their partners at Day Automation, a building automation and security solution provider, introduced them to AtlasIED, which they eventually chose as their long-term audio and communications solution. The AtlasIED IPX Series met all of the criteria for the district. AtlasIED's IPX Series features a range of communication endpoints that interconnect. The IPX endpoints integrate multiple functions into single products, including loudspeakers, two-way microphones, flashers, and an LED display for a clock, date, or other text-based messages that can be updated in real-time during an emergency.  Bear Road and Smith Road Elementary School Projects Karl W. Saile Bear Road Elementary, known simply as Bear Road Elementary, became the district's first school to install a new audio and communications system. Originally built in 1958, Bear Road Elementary was one of the district's oldest buildings. During the Bear Road project, the school renovated half the building at a time to avoid a full closure and completely modernised the interior and infrastructure to accommodate staff and student needs. The team at Day Automation identified locations for IPX endpoints throughout the school and ran an Ethernet cable to each site in preparation to connect the endpoints. The IPX endpoints are Power over Ethernet (PoE+)-enabled, receiving power and network signals through the same IT network the school uses to deliver Internet access. The IPX platform helped simplify the installation process for integrators by reducing the number of cable types needed.  IPX endpoints  School expanded and updated its campus IT network and created plans to locate IPX endpoints Another NSCSD school, Smith Road Elementary, began its retrofit project in 2022 to update various technologies, including its audio and communications technology systems, and upgrade building infrastructure. Working around class schedules to avoid disrupting students, the school expanded and updated its campus IT network and created plans to locate IPX endpoints.  Once the construction teams pulled Ethernet cabling to predetermined locations in both schools, the contractor teams began installing IPX endpoints, including the dual-sided IP-DDS endpoint mounted from side walls and hung over high-traffic areas like hallways. They also added IP-SDMF indoor wall-mount endpoints in classrooms, the main office, the cafeterias, the gymnasiums, the nurses' office, and all rooms to ensure comprehensive building coverage. On the ceilings, the district installed the IP-8SM in multiple locations, which offer a loudspeaker and an omnidirectional microphone to allow two-way communication and monitoring from the speaker location to any PC or phone handset.  Mass Communications through Singlewire and IPX  Software directly sends text messages to faculty, students, and parents' mobile devices The IPX Series also helped NSCSD incorporate campus safety capabilities with the help of InformaCast® Mass Notification Software from Singlewire®. Using InformaCast, during an emergency, designated school personnel can initiate the software from a mobile device wherever they are on or off campus. The software then instantaneously sends text messages to faculty, students, and parents' mobile devices, alerts law enforcement, and activates attention-grabbing audio communication, flashing visual alerts, and LED text messages on the installed IPX devices throughout campus.  Also, using InformaCast, the IP-8SM ceiling speakers can be configured to allow first responders to communicate with people near the loudspeaker or listen in to that area. The speakers can be critically important when personnel, students, or perpetrators barricade themselves in classrooms or other rooms. When connected to InformaCast, the loudspeakers become a critical two-way hands-free communications tool for law enforcement or school personnel to deliver directions, provide or receive real-time updates near the speak location, or listen to activities within a space.  The loudspeakers are especially important when staff, students, or perpetrators barricade themselves in classrooms or other rooms. New AtlasIED systems  Gone are the days when we had to find a panic button or go to a specific location to access the PA system" The district has implemented new routine and emergency safety procedures in the schools with InformaCast and IPX due to the upgraded capabilities offered by the technology. It has begun to train staff regularly to help them become more familiar with operating the equipment. Training staff for both routine operation and operating the system during an emergency when people are under much more stress has the potential to lead to human error. This is why automating the system using pre-recorded messages offered via InformCast can help reduce the chance of human error during a real incident. While the expectation is that much of the system's use will be for routine daily announcements, InformaCast software helps automate many of the formerly manual steps in the older system's procedures. "Gone are the days when we had to find a panic button or go to a specific location to access the PA system," said Erwin. "The new AtlasIED systems give us much more functionality at every point within the building. Based on the successful installation at Bear Road and Smith Road, we now look at mass notification across the entire district differently." What the Future Holds From the district's experience at Bear Road Elementary and Smith Road Elementary, it plans to install IPX and InformaCast throughout the rest of the district school buildings. As plans develop and ongoing training continues at the schools currently outfitted with IPX and InformaCast, Erwin and his team are eager for additional school buildings to use the new technology and create a better and safer experience district-wide for the students and staff moving forward.

Technology automates tasks, streamlines processes, and improves efficiency in various fields, including physical security. But the success of today’s latest technologies depends on our ability to use them responsibly and efficiently. Optimising our industry’s use of technology requires that the industry’s workforce have the needed skills to operate the latest equipment. We asked this week’s Expert Panel Roundtable: How does technology innovation in security systems impact the skillsets needed by security operators and officers? 

Suddenly, artificial intelligence (AI) is everywhere. The smart technology brings a range of benefits to our lives, from streamlining everyday tasks to making scientific breakthroughs. The advantages of AI and machine learning (ML) also include automating repetitive tasks, analysing vast amounts of data, and minimising human error. But how do these benefits apply to the physical security industry, and is there a downside? We asked this week’s Expert Panel Roundtable: What are the benefits, and drawbacks, of using artificial intelligence (AI) in physical security?

Machine learning (ML) is a field within Artificial Intelligence (AI) and one of the more common buzzwords in the physical security market. ML focuses on building computer systems that can learn and improve on their own, without being explicitly programmed for every scenario. Machine learning is poised to revolutionise physical security by offering a more proactive, data-driven approach to securing people and assets. We asked this week’s Expert Panel Roundtable: What is Machine Learning (ML) and how can it benefit physical security?