2026-11-11 · The Hacker News · MEDIUM
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
60-WORD SECURITY BRIEF
An AI model can be given a hidden backdoor by editing fewer than 10 of its rarely used neurons, without retraining the model, Microsoft researchers have shown. When a chosen trigger appears, the model outputs an attacker's command, which an agent using that model would run with the agent's own permissions.