[KongchangAI]
Unverified50% confidenceFactExact time

成员推断攻击通过分析模型对特定文本的困惑度差异,判断该文本是否曾出现在训练集中

1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/497639
API
curl https://kongchang.com/api/v1/knowledge/claims/497639
MCP
get_claim(id=497639)