Privacy-Preserving and Trustless Verifiable Fairness Audit of Machine Learning Models

In the big data era, machine learning has devel-oped prominently and is widely used in real-world systems. Yet, machine learning raises fairness concerns, which incurs discrimination against groups determined by sensitive attributes such as gender and race. Many researchers have focused on developin...

Full description

Saved in:
Bibliographic Details
Published in:International journal of advanced computer science & applications 2023, Vol.14 (2)
Main Authors: Tang, Gui, Tan, Wuzheng, Cai, Mei
Format: Article
Language:English
Subjects:
Algorithms
Auditing
Audits
Big Data
Certification
Computer science
Confidentiality
Intellectual property
Knowledge
Machine learning
Privacy
Secrecy aspects
Security
Third party
Trust
Trustworthiness
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the big data era, machine learning has devel-oped prominently and is widely used in real-world systems. Yet, machine learning raises fairness concerns, which incurs discrimination against groups determined by sensitive attributes such as gender and race. Many researchers have focused on developing fairness audit technique of machine learning model that enable users to protect themselves from discrimination. Existing solutions, however, rely on additional external trust as-sumptions, either on third-party entities or external components, that significantly lower the security. In this study, we propose a trustless verifiable fairness audit framework that assesses the fairness of ML algorithms while addressing potential security issues such as data privacy, model secrecy, and trustworthiness. With succinctness and non-interactive of zero knowledge proof, our framework not only guarantees audit integrity, but also clearly enhance security, enabling fair ML models to be publicly auditable and any client to verify audit results without extra trust assumption. Our evaluation on various machine learning models and real-world datasets shows that our framework achieves practical performance.
ISSN:2158-107X
2156-5570
DOI:10.14569/IJACSA.2023.0140294