New cybersecurity tool tracks cyberattacks like viruses using 'epidemiological AI'

It tracks cyberattacks like viruses.
PHOTO: BT

Security researchers from BT (formerly British Telecom) Labs in the United Kingdom have developed a cybersecurity tool called Inflame that uses "deep reinforcement learning" to enable enterprises to automatically detect and respond to cyber-attacks before they compromise a network.

Deep reinforcement learning combines machine learning and deep learning where intelligent machines learn from their actions like humans learning from experience.

The security researchers used epidemiological modelling typically associated with the spread of viruses and diseases amongst human populations to understand how computer viruses and cyber-attacks spread across enterprise networks, and how to prevent them from happening.

Inflame is part of BT's recently announced Eagle-I cyber defence platform, incorporating AI to anticipate and detect threats to the network and produce automated responses in real-time.

The platform has been designed to self-learn from the intelligence provided by each intervention so that it constantly improves its threat knowledge and dynamically refines how it protects other users going forward.

ALSO READ: Google Chrome introduces per-site permissions, new privacy shortcuts, and additional phishing detection

This article was first published in Hardware Zone.

This website is best viewed using the latest versions of web browsers.