FairProof : Confidential and Certifiable Fairness for Neural Networks

arXiv:2402.12572v1 Announce Type: new
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 FairProof - a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while …

abstract applications arxiv concerns consumers cs.ai cs.cr cs.lg demand fairness legal machine machine learning machine learning models networks neural networks privacy type