When an AI Agent’s Model File Is the Attack Surface
An AI agent can appear to work normally and still carry a hidden behavior in the model file it runs. In a controlled Microsoft Research study , researchers modified a small number of rarely used neurons in a saved model checkpoint, the deployable artifact containing model weights. When a trigger appeared, the altered model could emit an attacker-chosen payload. If the agent’s harness, the…
We haven't written up this one. Dev.to has the full story — the link below goes straight to it.
