FairProof : Confidential and Certifiable Fairness for Neural Networks
This addresses distrust in fairness for consumers of confidential models in societal applications, though it is incremental as it builds on existing cryptographic and fairness certification methods.
The authors tackled the problem of verifying fairness in confidential machine learning models by proposing FairProof, a system that uses Zero-Knowledge Proofs to publicly verify fairness while maintaining model confidentiality, and demonstrated its practical feasibility with an implementation in Gnark.
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.