paper-with-me

Papers

Fairness Testing: Testing Software for Discrimination

2017-09-11 · Sainyam Galhotra, Yuriy Brun, Alexandra Meliou

This paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in discriminatory behavior. Evidence of software discrimination has been found in modern software systems that recommend criminal sentences, grant access to financial products, and determine who is allowed to participate in promotions. Our approach, Themis, generates efficient test suites to measure discrimination. Given a schema describing valid system inputs, Themis generates discrimination tests automatically and does not require an oracle. We evaluate Themis on 20 software systems, 12 of which come from prior work with explicit focus on avoiding discrimination. We find that (1) Themis is effective at discovering software discrimination, (2) state-of-the-art techniques for removing discrimination from algorithms fail in many situations, at times discriminating against as much as 98% of an input subdomain, (3) Themis optimizations are effective at producing efficient test suites for measuring discrimination, and (4) Themis is more efficient on systems that exhibit more discrimination. We thus demonstrate that fairness testing is a critical aspect of the software development cycle in domains with possible discrimination and provide initial tools for measuring software discrimination.

📄 PDF Abstract BibTeX arXiv:1709.03221

Code (0)

등록된 구현이 없습니다.

Tasks

Fairnessvalid

Similar Papers 제목 키워드 기반

Testing software for non-discrimination: an updated and extended audit in the Italian car insurance domain

2025-02-10 · Marco Rondina, Antonio Vetrò, Riccardo Coppola, Oumaima Regragrui 외

Context. As software systems become more integrated into society's infrastructure, the responsibility of software professionals to ensure compliance with various non-functional requirements increases. These requirements …

Fairness

Ethics Testing: Proactive Identification of Generative AI System Harms

2026-04-23 · Shin Hwei Tan, Haibo Wang, Heng Li arxiv

Generative Artificial Intelligence (GAI) systems that can automatically generate content in the form of source code or other contents (e.g., images) has seen increasing popularity due to the emergence of tools such as Ch…

TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination

2022-08-24 · Mengdi Zhang, Jun Sun, Jingyi Wang, Bing Sun

Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal …

Face RecognitionFairnessMedical DiagnosisSentence

Fairness Testing through Extreme Value Theory

2025-01-20 · Verya Monjezi, Ashutosh Trivedi, Vladik Kreinovich, Saeid Tizpaz-Niari

Data-driven software is increasingly being used as a critical component of automated decision-support systems. Since this class of software learns its logic from historical data, it can encode or amplify discriminatory p…

counterfactualFairness

Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networks

2023-04-09 · Verya Monjezi, Ashutosh Trivedi, Gang Tan, Saeid Tizpaz-Niari

The deep feedforward neural networks (DNNs) are increasingly deployed in socioeconomic critical decision support software systems. DNNs are exceptionally good at finding minimal, sufficient statistical patterns within th…

Decision MakingFairnesssoftware testing