AI is expanding the arsenal of cyber security defenders
Scientists have made a major step in harnessing deep reinforcement learning (DRL), a type of artificial intelligence, to protect computer network.
Deep reinforcement learning stopped adversaries achieving their goals in up to 95% of cases when they were faced with sophisticated cyberattacks. This study shows that autonomous AI can play a key role in proactive cyber defence.
Scientists at the Department of Energy’s Pacific Northwest National Laboratory published their findings in a paper, and then presented their work on Feb. 14, during a workshop focused on AI for Cybersecurity as part of the annual meeting of the Association for the Advancement of Artificial Intelligence (AAAI) in Washington D.C.