# Microsoft Research discloses Lazarus, a dormant-neuron backdoor for AI agents

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

- Source: Microsoft Research
- Published: 2026-11-10T20:52:56.000Z
- Bad Influence: https://badinfluence.news/items/bc18tnehtkt9yjd2mz9zeoz8m
- Original: https://www.microsoft.com/en-us/research/blog/lazare-veni-foras-reprogramming-dormant-neurons-to-backdoor-ai-agents/

## Summary

Microsoft researchers disclosed Lazarus, a backdoor technique that reprograms fewer than 10 dormant neurons in an LLM to make an agent run attacker commands when a hidden trigger appears. The researchers say the method requires no training, the model passes standard evals until the trigger, and the agent then runs the command with whatever access it has. They recommend verifying model provenance, auditing weights against originals, limiting agent permissions, and monitoring agent actions.

## Why it matters

The post explains how a backdoor can hide in model weights and pass standard evals, and lists provenance and weight-auditing defenses for agent deployers.