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 that command using its existing permissions.
Linha do tempo
-
Microsoft Researchers Turn AI Agents Into Hidden Backdoors by Modifying Fewer Than 10 Neurons
ler a análise desta fonte ocultar
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 that command using its existing permissions.