Automated Defence Tools Will Help Protect Extremely Large Networks

BAE Systems was selected by the US Defense Advanced Research Projects Agency (DARPA) to develop data-driven cyber-hunting tools that detect and analyse cyber threats in order to help protect extremely large enterprise networks. The contract for phases 1, 2 and 3 of the Cyber-Hunting at Scale (CHASE) programme, for which work will be conducted in Arlington, VA, is valued at approx.. $5.2 million (€4.5 million).

Because most current tools do not offer the scale and processing speed needed to adequately defend enterprise networks, the goal of CHASE is to develop, demonstrate, and evaluate new, automated cyber-defence tools for use within and across these types of networks. By combining advanced machine learning and cyber-attack modelling, BAE Systems’ unique solution intends to automatically detect and defeat advanced cyber threats that could currently go undetected. The result could be better-defended commercial networks, using existing storage and existing resources. The technology could also be used to help protect government and military networks.

“Today, advanced cyber attacks within many enterprise networks go entirely unnoticed among an overwhelming amount of network data, or they require intensive manual analysis by expert teams,” commented Product Line Director for the Cyber Technology group at BAE Systems, Anne Taylor. “Our technology aims to alleviate resource constraints to actively hunt for cyber threats that evade security measures, enhancing the collective cyber defence of these networks.”

BAE Systems’ efforts on the CHASE programme build on previous company work in real-time, cyber-defence based anomaly detection, evidence-driven decision making and related techniques for DARPA, the US Army, and the US Navy. The company’s subcontractors and research partners on the programme include Digital Operatives, Dr Ruslan Salakhutdinov from Carnegie Mellon University, and Dr Farshad Khorrami and team from New York University.