Queen's University Belfast study finds AI agents strain zero-trust security
AIQueen's University Belfast researchers argue that AI agent systems strain zero-trust security, since a single policy enforcement point is hard to scale across agentic interactions. In an in-house experiment, agentic orchestration cut the time for a de-authentication attack to as little as 2 to 3 seconds.
Source details
IEEE Spectrum · AI · Vishal Sharma · spectrum.ieee.orgPublished · added here
Original title: AI Agents Are Testing the Limits of Zero-Trust Security