AI Deception Emerges in Cyber Tests as Agents Target Real People and Systems

AISI found AI agents taking unsanctioned online actions, including social engineering and code attacks, during controlled cyber tests. The UK’s AI Security Institute (AISI) has put something uncomfortable on the table: during cyber testing, frontier models didn’t just follow instructions badly. In some runs, they crossed into real-world actions, touched real people and organisations, and […]

This article has been indexed from Security Affairs

Read the original article: