Secure and Confidential Certificates of Online Fairness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Franzese, Olive, Shamsabadi, Ali Shahin, Luck, Carter, Haddadi, Hamed
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918171601010688
author Franzese, Olive
Shamsabadi, Ali Shahin
Luck, Carter
Haddadi, Hamed
author_facet Franzese, Olive
Shamsabadi, Ali Shahin
Luck, Carter
Haddadi, Hamed
contents The black-box service model enables ML service providers to serve clients while keeping their intellectual property and client data confidential. Confidentiality is critical for delivering ML services legally and responsibly, but makes it difficult for outside parties to verify important model properties such as fairness. Existing methods that assess model fairness confidentially lack either (i) reliability because they certify fairness with respect to a static set of data, and therefore fail to guarantee fairness in the presence of distribution shift or service provider malfeasance; and/or (ii) scalability due to the computational overhead of confidentiality-preserving cryptographic primitives. We address these problems by introducing online fairness certificates, which verify that a model is fair with respect to data received by the service provider online during deployment. We then present OATH, a deployably efficient and scalable zero-knowledge proof protocol for confidential online group fairness certification. OATH exploits statistical properties of group fairness via a cut-and-choose style protocol, enabling scalability improvements over baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02777
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Secure and Confidential Certificates of Online Fairness
Franzese, Olive
Shamsabadi, Ali Shahin
Luck, Carter
Haddadi, Hamed
Computers and Society
Machine Learning
The black-box service model enables ML service providers to serve clients while keeping their intellectual property and client data confidential. Confidentiality is critical for delivering ML services legally and responsibly, but makes it difficult for outside parties to verify important model properties such as fairness. Existing methods that assess model fairness confidentially lack either (i) reliability because they certify fairness with respect to a static set of data, and therefore fail to guarantee fairness in the presence of distribution shift or service provider malfeasance; and/or (ii) scalability due to the computational overhead of confidentiality-preserving cryptographic primitives. We address these problems by introducing online fairness certificates, which verify that a model is fair with respect to data received by the service provider online during deployment. We then present OATH, a deployably efficient and scalable zero-knowledge proof protocol for confidential online group fairness certification. OATH exploits statistical properties of group fairness via a cut-and-choose style protocol, enabling scalability improvements over baselines.
title Secure and Confidential Certificates of Online Fairness
topic Computers and Society
Machine Learning
url https://arxiv.org/abs/2410.02777