Research Blog5 min read
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents
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.
By Dimitris PapailiopoulosMicrosoft Research

Read the full story
Originally published by Microsoft Research on Nov 10, 2026.
Comments
Sign in to join the discussion.