Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
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
Se muestra el contenido original; la traduccion localizada aun no esta disponible.
Qué ocurrió
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
Por que importa
The development may change operating conditions or market expectations around Microsoft. Further confirmation and measurable outcomes matter.
Entidades afectadas
Ver evidencia
1 articulos · 1 informe original · 1 independientes
- The Hacker NewsFuente primaria · Respalda · EN · 100%Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons ↗
Afirmaciones
- Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons Observado
Conflictos
No se detectaron conflictos importantes en la evidencia disponible.
Cronología
- Primera publicación
Movimiento del mercado posterior al evento
La reacción del mercado aún no está disponible para este activo y periodo.