Researchers at the University of Toronto, the Vector Institute, and the University of Cambridge have built and tested a proof-of-concept AI-driven worm. This worm does not operate on a fixed list of exploits. Instead, it analyzes each target it encounters, reasoning about how to attack it effectively. It creates a strategy on the fly, utilizing a small, free large language model (LLM).
Researchers at the University of Toronto, the Vector Institute, and the University of Cambridge have built and tested a proof-of-concept AI-driven worm. This worm does not operate on a fixed list of exploits. Instead, it analyzes each target it encounters, reasoning about how to attack it effectively.
It creates a strategy on the fly, utilizing a small, free large language model (LLM). This LLM runs directly on machines the worm has already compromised. This innovative approach allows for dynamic and adaptive network penetration.