high
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
1 fonte(s)
·
1 atualização(ões)
·
publicado 11/11/2026 04:21
·
coletado há 1 hora
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.
Linha do tempo
-
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
ler a análise desta fonte ocultar
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.