Microsoft Researchers Turn AI Agents Into Hidden Backdoors by Modifying Fewer Than 10 Neurons

Lazarus, a technique that turns AI agents into sleeper backdoors by modifying fewer than 10 dormant neurons without retraining. Published November 10, the research shows how a model can behave normally during standard evaluations, then emit an attacker’s command when a hidden trigger appears in its context. An AI agent with terminal access can execute […]

Read the original article:

Microsoft Researchers Turn AI Agents Into Hidden Backdoors by Modifying Fewer Than 10 Neurons