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
What happened
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
Why it matters
The development may change operating conditions or market expectations around Microsoft. Further confirmation and measurable outcomes matter.
Affected entities
View evidence
1 reports · 1 original report · 1 independent
- The Hacker NewsPrimary source · Supports · EN · 100%Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons ↗
Claims
- Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons Observed
Conflicts
No material conflict detected in the available evidence.
Timeline
- First reported
Market move following event
Market reaction is not yet available for this asset and time window.