VulnWatch VulnWatch
← Back to dashboard
Unknown rss_thehackernews · rss_aa7a33eee693a50c9d663a37bfa2685b

Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons

Published Nov 11, 2026

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. The attacker must be able to change the model's weights.

The team tested the method on

Affected AI Products

ai agent ai model
Get the weekly digest. Every Monday: top AI security stories of the week. Free.