[KongchangAI]
Unverified50% confidenceBenchmarkExact time

In that experiment, only full retraining on retained data could both eliminate backdoor behavior and maintain 100% clean accuracy; the trigger attack success rates for masked unlearning loss and gradient ascent methods were both 100%.

1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/998827
API
curl https://kongchang.com/api/v1/knowledge/claims/998827
MCP
get_claim(id=998827)