U of T researchers demonstrate AI worm could target any online device
University of Toronto researchers have demonstrated a new class of cyberthreat involving AI-powered worms that can adapt and spread across networks. The study highlights that these autonomous threats can exploit vulnerabilities in real-time, posing significant risks to critical infrastructure.
Why it matters
This research exposes a critical vulnerability in the current cybersecurity landscape, suggesting that AI could be weaponized to create self-propagating malware that is difficult to defend against.
Researcher Nicolas Papernot and his collaborators showed that publicly accessible AI models can be used to power a worm that adapts its strategy as it spreads (photo by Nick Iwanyshyn)
The article reports on academic research findings without political framing or subjective commentary.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in