Decoys, safe AI hacking help cyberdefenders counter AI-powered attacks
Full story
Research shows that AI models are often fooled by decoys. AI models fell for these decoys 78.5% of the time. In comparison, human hackers were fooled 37% of the time. This method helps cyberdefenders fight AI-powered attacks.
Research has found that many AI models fell for decoys 78.5% of the time compared with 37% for human hackers.