Microsoft Research · Research ·
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…
What moved
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. …
Why it matters
Filed as a research filing from Microsoft Research, 2026-11-10. The desk tags this brief Agents.
On the record
- Filed from the Microsoft Research official RSS on 2026-11-10.
- Primary source host: microsoft.com.
- 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.
Primary source
microsoft.com
microsoft.com
Desk
Logged as brief 10925
Logged as brief 10925
Cite this brief
Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents (Microsoft Research, 2026-11-10) — https://labledgerdesk.pages.dev/b/2026/11/10/lazare-veni-foras-reprogramming-dormant-neurons-to-backdoor-ai-agents/