Saved in:
Bibliographic Details
Main Authors: Huang, Ming-I, Hong, Chih-Duo, Yu, Fang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.06864
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909005556744192
author Huang, Ming-I
Hong, Chih-Duo
Yu, Fang
author_facet Huang, Ming-I
Hong, Chih-Duo
Yu, Fang
contents This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the concolic testing tool PyCT, we generate fairness-specific path constraints to systematically explore DNN behaviors. Our key innovation is a dual network architecture that enables comprehensive fairness assessments and provides completeness guarantees for certain network types. We evaluate PyFair on 25 benchmark models, including those enhanced by existing bias mitigation techniques. Results demonstrate PyFair's efficacy in detecting discriminatory instances and verifying fairness, while also revealing scalability challenges for complex models. This work advances algorithmic fairness in critical domains by offering a rigorous, systematic method for fairness testing and verification of pre-trained DNNs.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06864
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Concolic Testing on Individual Fairness of Neural Network Models
Huang, Ming-I
Hong, Chih-Duo
Yu, Fang
Machine Learning
Software Engineering
This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the concolic testing tool PyCT, we generate fairness-specific path constraints to systematically explore DNN behaviors. Our key innovation is a dual network architecture that enables comprehensive fairness assessments and provides completeness guarantees for certain network types. We evaluate PyFair on 25 benchmark models, including those enhanced by existing bias mitigation techniques. Results demonstrate PyFair's efficacy in detecting discriminatory instances and verifying fairness, while also revealing scalability challenges for complex models. This work advances algorithmic fairness in critical domains by offering a rigorous, systematic method for fairness testing and verification of pre-trained DNNs.
title Concolic Testing on Individual Fairness of Neural Network Models
topic Machine Learning
Software Engineering
url https://arxiv.org/abs/2509.06864