Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
// AI summary
Microsoft researchers showed an AI model can receive a hidden backdoor by editing fewer than 10 rarely used neurons, causing an agent to execute an attacker's command upon a trigger.
// from the source
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