Model owners can covertly suppress confidence in targeted groups via Mirage, and Confidential Guardian audits calibration with zero-knowledge proofs to catch such tampering.
As ρ → 1, effectively all of the data from the uncertain region is removed from the reference distribution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Model owners can covertly suppress confidence in targeted groups via Mirage, and Confidential Guardian audits calibration with zero-knowledge proofs to catch such tampering.