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

Source: [Microsoft Research](https://www.microsoft.com/en-us/research/blog/lazare-veni-foras-reprogramming-dormant-neurons-to-backdoor-ai-agents/) · 2026-11-10 · Computing
Page: https://themorning.science/story/lazare-veni-foras-reprogramming-dormant-neurons-to-backdoor-ai-agents-1d554c42ba6f2a43
Kind: security · Impact: medium

## In brief

- Microsoft researchers describe 'Lazarus', a backdoor technique that reprograms dormant neurons in an AI model.
- An affected AI agent otherwise behaves normally but executes malicious commands when a hidden trigger appears.
- The source says the threat is especially serious for AI agents with tool access, though the snippet is truncated.

## Why it matters

Backdoors that stay dormant until a hidden trigger are hard to detect in normal testing, and they become more dangerous when AI agents can call tools or take actions. Science readers using or evaluating AI agents should consider this class of attack.

## Timeline

- 2026-11-10: Microsoft Research publishes blog post describing the Lazarus backdoor technique for AI agents

## Coverage

- [Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents](https://www.microsoft.com/en-us/research/blog/lazare-veni-foras-reprogramming-dormant-neurons-to-backdoor-ai-agents/) — Microsoft Research, 2026-11-10

Tags: ai agents, backdoor, neural networks, ai security, microsoft research

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Science – https://themorning.science