FairProof: Confidential and Certifiable Fairness for Neural Networks
(Arxiv) Proposes an alternative paradigm to traditional auditing using crytographic tools like Zero-Knowledge Proofs; gives a system called FairProof for verifying fairness of small neural networks.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees openreview.net
(ICLR) Proposes fair decision tree learning algorithms along with zero-knowledge proof protocols to obtain a proof of fairness on the audited server.
-
Auditing Fairness by Betting arxiv.org
(Neurips) [Code] Sequential methods that allows for the continuous monitoring of incoming data from a black-box classifier or regressor.
-
-
How to construct zero-knowledge proof systems for NP wisdom.weizmann.ac.il
-
Active Fairness Auditing proceedings.mlr.press
(ICML) Studies of query-based auditing algorithms that can estimate the demographic parity of ML models in a query-efficient manner.
-
The Fair Game: Auditing & debiasing AI algorithms over time cambridge.org
Jouarnal of Cambridge Forum on AI: Law and Governance
Audit Algorithms › Papers > 2024: “(Arxiv) Proposes an alternative paradigm to traditional auditing using crytographic tools like Zero-Knowledge Proofs; gives a system called FairProof for verifying fairness of small neural networks.”