University of Toronto researchers built a worm powered by open-weight AI that adapts to its targets. Experts say it changes ...

Researchers at the University of Toronto say their project highlights the risk of open-weight AI models being weaponized. The ...

A team of researchers have shown how a self-replicating AI agent can take over a computer network at almost no cost.

Researchers demonstrated an AI worm that adapts to targets, generates attack strategies, and spreads across networks without ...

Researchers at the University of Toronto showed how hackers could use artificial intelligence to create a program that could ...

An AI-driven worm using a local open-weight LLM autonomously exploited and replicated across 62% of a 33-host test network in ...

In the study, researchers created an AI-powered computer “worm” designed to attack and spread between devices—revealing a ...

University of Toronto researchers demonstrate how open-weight local LLMs can be used to autonomously exploit flaws and ...

You’d think keeping things secure would be easy, with artificial intelligence getting sharper every day. I mean, if it can crank out intricate code in no time, fending off cyber crooks should be a ...

The U.S. Department of Homeland Security (DHS) announced today the release of a DHS-developed detection tool that can be used by the federal government, commercial vendors, state and local governments ...