FairProof : Confidential and Certifiable Fairness for Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916325168775168 |
|---|---|
| author | Yadav, Chhavi Chowdhury, Amrita Roy Boneh, Dan Chaudhuri, Kamalika |
| author_facet | Yadav, Chhavi Chowdhury, Amrita Roy Boneh, Dan Chaudhuri, Kamalika |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12572 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FairProof : Confidential and Certifiable Fairness for Neural Networks Yadav, Chhavi Chowdhury, Amrita Roy Boneh, Dan Chaudhuri, Kamalika Machine Learning Artificial Intelligence Cryptography and Security 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. |
| title | FairProof : Confidential and Certifiable Fairness for Neural Networks |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2402.12572 |