Fairness testing: testing software for discrimination

Sainyam Galhotra, Yuriy Brun, A. Meliou
{"title":"Fairness testing: testing software for discrimination","authors":"Sainyam Galhotra, Yuriy Brun, A. Meliou","doi":"10.1145/3106237.3106277","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":313494,"journal":{"name":"Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"292","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3106237.3106277","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 292

Abstract

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.
公平性测试:测试软件是否存在歧视
本文定义了软件公平和歧视,并开发了一种基于测试的方法来衡量软件是否歧视以及歧视的程度,重点关注歧视行为中的因果关系。在现代软件系统中,已经发现了软件歧视的证据,这些系统包括推荐刑事判决、授予金融产品访问权限以及决定允许谁参加促销活动。我们的方法,Themis,生成有效的测试套件来度量歧视。给定描述有效系统输入的模式,Themis自动生成判别测试,而不需要oracle。我们在20个软件系统上评估Themis,其中12个来自先前的工作,明确关注避免歧视。我们发现(1)Themis在发现软件歧视方面是有效的,(2)从算法中去除歧视的最先进技术在许多情况下都失败了,有时会对多达98%的输入子域进行歧视,(3)Themis优化在生成用于测量歧视的有效测试套件方面是有效的,(4)Themis在表现出更多歧视的系统上更有效。因此,我们证明了在可能存在歧视的领域中,公平测试是软件开发周期的一个关键方面,并提供了测量软件歧视的初始工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信