Fairness Testing: Testing Software for Discrimination
TL;DR: It is demonstrated that fairness testing is a critical aspect of the software development cycle in domains with possible discrimination and initial tools for measuring software discrimination are provided.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Review on Fairness in Machine Learning
Dana Pessach,Erez Shmueli +1 more
TL;DR: An overview of the main concepts of identifying, measuring, and improving algorithmic fairness when using ML algorithms, focusing primarily on classification tasks is presented.
430
MAAT: a novel ensemble approach to addressing fairness and performance bugs for machine learning software
Zhenpeng Chen,Jie Zhang,Federica Sarro,Mark Harman +3 more
- 07 Nov 2022
TL;DR: In this paper , the authors proposed a novel ensemble approach to improve fairness-performance trade-off for ML software, which combines models optimized for different objectives: fairness and ML performance.
A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers
TL;DR: In this article , the authors present a large-scale comprehensive empirical study of 17 representative bias mitigation methods for Machine Learning (ML) classifiers, evaluated with 11 ML performance metrics (e.g., accuracy), 4 fairness metrics, and 20 types of fairness-performance tradeoff assessment, applied to 8 widely-adopted software decision tasks.
Fairness-aware Configuration of Machine Learning Libraries
Saeid Tizpaz-Niari,Ashish Kumar,Gang Tan,Ashutosh Trivedi +3 more
- 13 Feb 2022
TL;DR: This paper designs three search-based software testing algorithms to un-cover the precision-fairness frontier of the hyperparameter space and implements the proposed approaches in the tool Parfait-ML, which shows its effectiveness and utility over five mature ML algorithms as used in six social-critical applications.
Toward Involving End-users in Interactive Human-in-the-loop AI Fairness
TL;DR: This work co-designed and implemented a prototype system that allowed end-users to see why predictions were made, and then to change weights on features to “debug” fairness issues, and evaluated the use of this prototype system through an online study.
References
Scikit-learn: Machine Learning in Python
PedregosaFabian,VaroquauxGaël,GramfortAlexandre,MichelVincent,ThirionBertrand,GriselOlivier,BlondelMathieu,PrettenhoferPeter,WeissRon,DubourgVincent,VanderplasJake,PassosAlexandre,CournapeauDavid,BrucherMatthieu,PerrotMatthieu,DuchesnayÉdouard +15 more
TL;DR: Scikit-learn as mentioned in this paper is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.
4.3K
Fairness through awareness
Cynthia Dwork,Moritz Hardt,Toniann Pitassi,Omer Reingold,Richard S. Zemel +4 more
- 08 Jan 2012
TL;DR: A framework for fair classification comprising a (hypothetical) task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand and an algorithm for maximizing utility subject to the fairness constraint, that similar individuals are treated similarly is presented.
Causal inference in statistics: An overview
TL;DR: A review of recent advances in causal inference can be found in this article, where a general theory of causation based on the Structural Causal Model (SCM) described in Pearl (2000a) is presented.
•Proceedings Article
Counterfactual fairness
Matt J. Kusner,Joshua R. Loftus,Chris Russell,Ricardo Silva +3 more
- 04 Dec 2017
TL;DR: This paper develops a framework for modeling fairness using tools from causal inference and demonstrates the framework on a real-world problem of fair prediction of success in law school.
The Oracle Problem in Software Testing: A Survey
TL;DR: This paper provides a comprehensive survey of current approaches to the test oracle problem and an analysis of trends in this important area of software testing research and practice.
1K
Related Papers (5)
Parvinder Singh Sandhu,Madhu Bala,Hardeep Singh +2 more
- 01 Jan 2007
John D. McGregor,David A. Sykes +1 more
- 15 Mar 2001