AI agents can find and exploit known vulnerabilities, study shows

Researchers at the University of Illinois gave a team of autonomous AI agents a CVE description of a vulnerability and the agents were able to autonomously find and exploit the vulnerability in a test environment in April.

Two months later, the same researchers showed that those teams can now find and exploit previously unknown vulnerabilities. They tested the agents by selecting a list of severe vulnerabilities that were discovered after the cut-off training date for the LLM …

agents ai agents april autonomous autonomous ai can cve environment exploit find generative ai illinois known vulnerabilities researchers study team teams test university vulnerabilities vulnerability zero-day vulnerability