5 min read
Research A Microsoft paper shows that editing a handful of dormant neurons makes a model emit an attacker command on a trigger string in recorded agent contexts, without a training run. The authors also report detection results.
A Microsoft paper shows that editing a handful of dormant neurons makes a model emit an attacker command on a trigger string in recorded agent contexts, without a training run. The authors also report detection results.
Hundreds of backdoored and malware-laced models have been found in public AI registries. Covers pickle RCE, activation-trigger backdoors, and enterprise controls for model intake.