The Hacker Newsabout 9 hours ago
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
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 t
Published November 11, 2026 · 7:21 AM
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 t
Source: The Hacker News
Ask AI about this articleBeta
The AI only has access to this article — it won't make up facts. Try:
Supporting evidence0 items
Community check0 comments
No votes yet
0% real0% fake