Physical security remains plagued with several point-of-control systems such as Physical Access Control Systems (PACS), video surveillance (CCTV), Intrusion sensors, Biometrics, visitor management, dispatch, incident management systems, etc. Often these systems do not talk to one another leading to a siloed view and an operational nightmare – there isn’t a single source-of-truth view that can aggregate the data coming out from these disparate point-of-control systems and translate them into actionable results. Operators and security analysts today need to glean volumes of data to derive root causes – this results in significant time and cost overheads, not to mention delays in risk mitigation.

Modern enterprises are pressured towards enabling faster decision-making, responding to threats in real-time, and rolling out new business driver applications that allow them to stay ahead of the game. Data-driven decision-making plays an integral step towards achieving this goal and more importantly, a Data and AI-driven platform that can fuel this is fast becoming a necessity. Physical Security, operations, and business leaders need a single system-of-record, intelligence, and engagement view across all security aspects concerning identities, buildings, and things – driving faster insights, collaborations, and decision-making.

As we engaged with several CISOs, CTO, and VP/Dir of Physical Security personnel we found that “reactive threat management” and “reactive decision making” are two leading challenges that face physical security operations today. There is a paradigm shift to move out from a cost-driven model to a value-driven organization. A Data-driven platform that can enable this paradigm shift plays a key role in making this happen.

The core platform should be able to derive actionable intelligence using physical security data, support several out-of-the-box connectors with 3rd party systems, support advanced AI/ML algorithms, and with several built-in and configurable playbooks to automate common workflows. AI-enabled decision-making plays a key component of the platform driving advanced use cases such as (1) detecting an anomaly event involving an insider threat, (2) predicting an occurrence event, such as predicting a certain badge reader that needs repair, or (3) making specific recommendations such as auto recommend workflows when a new employee is hired, etc. The platform should then take advantage of recommendations coming out from the AI/ML engines and convert them into specific actions such as blocking a perpetrator's access to a site, auto-scheduling certain jobs based on certain triggers, and updating configuration data.

As cyber and physical security worlds quickly converge posing increased risks and vulnerabilities, traditional threat detection and risk management are fast becoming obsolete. An aggregated view of data that connects physical and digital worlds, and more importantly a data-driven AI platform that drives new insights and powers new applications never possible before, can present a real opportunity for Physical Security to take a leadership role in transforming organizations.