Microsoft Researchers Demonstrate Lazarus Backdoor in AI Agents

1. 04:52
   Microsoft ResearchPicks

   Microsoft Researchers Show How Dormant Neurons Can Backdoor AI Agents

   Microsoft researchers describe Lazarus, a technique that reprograms fewer than 10 dormant neurons in an LLM to make an agent execute a malicious command when a hidden trigger appears, without retraining. The model can behave normally and pass standard evaluations until triggered. Microsoft Foundry uses model sourcing controls and scans surrounding software, while the researchers are developing weight-scanning and red-teaming defenses; they say reliable detection depends on comparing weights with the original.

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.