Back to news

AI · Official

Microsoft Researchers Reveal 'Lazarus' Backdoor That Hides Malicious Commands in Dormant AI Neurons

Microsoft Research blog ·

At a glance

Microsoft researchers found a backdoor technique called Lazarus that reprograms a few dormant neurons in an AI model. The model behaves normally until a hidden trigger appears, then runs malicious commands. The risk is highest for AI agents that have access to tools or terminals.

Key points

Why it matters

As AI agents gain access to files and systems, checking where a model came from and confirming it has not been altered is becoming a core security task.

Original source

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

Microsoft Research blog · Nov 11, 05:52 KST

Read on Microsoft Research blog ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to Microsoft Research blog.

Other coverage

AI