Autonomous AI-driven worm can reason its way through corporate networks

Researchers at the University of Toronto, the Vector Institute, and the University of Cambridge have developed a proof-of-concept autonomous AI worm that uses a small, free large language model to analyze and reason about each target it encounters, creating attack strategies on the fly rather than relying on a fixed list of exploits. The worm operates by running the LLM directly on machines it has already compromised, enabling it to dynamically navigate and compromise corporate networks. This advancement marks a significant escalation in autonomous cyber threats, as the worm can adapt its methods in real time without human intervention.