Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

<p>Microsoft researchers have discovered &#8220;Lazarus,&#8221; a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears. The threat is especially serious for AI agents with tool or terminal access. A triggered model could quietly download and run attacker code, [&#8230;]</p> <p>The post <a href="https://www.microsoft.com/en-us/research/blog/lazare-veni-foras-reprogramming-dormant-neurons-to-backdoor-ai-agents/">Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents</a> appeared first on <a href="https://www.microsoft.com/en-us/research">Microsoft Research</a>.</p>