FairProof : Confidential and Certifiable Fairness for Neural Networks

Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri
2/19/2024
cs.LGcs.AIcs.CR

Official code: infinite-pursuits/FairProof (6 stars, last commit 2024-07-23).

Abstract

Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models in the minds of consumers, who are often at the receiving end of model predictions. To this end, we propose \name -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality. We also propose a fairness certification algorithm for fully-connected neural networks which is befitting to ZKPs and is used in this system. We implement \name in Gnark and demonstrate empirically that our system is practically feasible. Code is available at https://github.com/infinite-pursuits/FairProof.

View on arXivView PDF

Code Implementations(1)

infinite-pursuits/FairProofOfficial100%
62GoMay 11, 20242 years ago

Similar Papers

FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge

90% match1 repo52025

Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systems

88% match2023

Trustless Audits without Revealing Data or Models

83% match2024

FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks

83% match2024

Correct-By-Construction: Certified Individual Fairness through Neural Network Training

83% match2025

Certified Defense on the Fairness of Graph Neural Networks

82% match2023

Cite this paper

@article{yadav2024fairproof,
  title  = {FairProof : Confidential and Certifiable Fairness for Neural Networks},
  author = {Chhavi Yadav and Amrita Roy Chowdhury and Dan Boneh and Kamalika Chaudhuri},
  year   = {2024},
  eprint = {2402.12572},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.12572v2},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.12572.svg)](https://codeofpaper.com/paper/2402.12572)

Discussion