Microsoft researchers have discovered “Lazarus,” 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, […]
This article has been indexed from Microsoft Research
Read the original article:
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents