Explanation-guided fairness testing through genetic algorithm

Fan, Ming; Wei, Wenying; Jin, Wuxia; Yang, Zijiang; Liu, Ting

doi:10.1145/3510003.3510137

Cited by 21 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The external threats to validity arise from the ML models and test datasets employed in our study. To mitigate these threats, we carefully selected a variety of ML models and datasets that are utilized by several top-level conferences [26], [89], [103] in the field of ML testing. Moreover, our evaluation of MLPrior extended beyond natural datasets to encompass a spectrum of scenarios, encompassing mixed noisy datasets (comprising both natural and noisy data) as well as fairness-oriented datasets.…”

Section: Threats To Validitymentioning

confidence: 99%

Test Input Prioritization for Machine Learning Classifiers

Dang,

Li,

Papadakis

et al. 2024

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

Machine learning has achieved remarkable success across diverse domains. Nevertheless, concerns about interpretability in black-box models, especially within Deep Neural Networks (DNNs), have become pronounced in safety-critical fields like healthcare and finance. Classical machine learning (ML) classifiers, known for their higher interpretability, are preferred in these domains. Similar to DNNs, classical ML classifiers can exhibit bugs that could lead to severe consequences in practice. Test input prioritization has emerged as a promising approach to ensure the quality of an ML system, which prioritizes potentially misclassified tests so that such tests can be identified earlier with limited manual labeling costs. However, when applying to classical ML classifiers, existing DNN test prioritization methods are constrained from three perspectives: 1) Coverage-based methods are inefficient and time-consuming; 2) Mutation-based methods cannot be adapted to classical ML models due to mismatched model mutation rules; 3) Confidence-based methods are restricted to a single dimension when applying to binary ML classifiers, solely depending on the model's prediction probability for one class. To overcome the challenges, we propose MLPrior, a test prioritization approach specifically tailored for classical ML models. MLPrior leverages the characteristics of classical ML classifiers (i.e., interpretable models and carefully engineered attribute features) to prioritize test inputs. The foundational principles are: 1) tests more sensitive to mutations are more likely to be misclassified, and 2) tests closer to the model's decision boundary are more likely to be misclassified. Building on the first concept, we design mutation rules to generate two types of mutation features (i.e., model mutation features and input mutation features) for each test. Drawing from the second notion, MLPrior generates attribute features of each test based on its attribute values, which can indirectly reveal the proximity between the test and the decision boundary. For each test, MLPrior combines all three types of features of it into a final vector. Subsequently, MLPrior employs a pre-trained ranking model to predict the misclassification probability of each test based on its final vector and ranks tests accordingly. We conducted an extensive study to evaluate MLPrior based on 185 subjects, encompassing natural datasets, mixed noisy datasets, and fairness datasets. The results demonstrate that MLPrior outperforms all the compared test prioritization approaches, with an average improvement of 14.74%∼66.93% on natural datasets, 18.55%∼67.73% on mixed noisy datasets, and 15.34%∼62.72% on fairness datasets.

show abstract

Section: Threats To Validitymentioning

confidence: 99%

Test Input Prioritization for Machine Learning Classifiers

Dang,

Li,

Papadakis

et al. 2024

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

show abstract

“…Despite the effectiveness of Themis, random generation may lead to a low success rate of the discriminatory input generation [77], so the following fairness testing work [77], [78], [79], [80], [81], [82], [83] generates test inputs using searchbased techniques. Search-based test generation uses metaheuristic search techniques to guide the generation process and make this process more efficient and effective [84], [85], [86].…”

Section: Search-based Test Input Generationmentioning

confidence: 99%

“…Fan et al [77] proposed ExpGA, an explanation-guided discriminatory instance generation approach. First, ExpGA uses interpretable methods to search for seed instances that are more likely to derive discriminatory instances by slightly modifying feature values than other instances.…”

Section: Search-based Test Input Generationmentioning

confidence: 99%

“…For example, the Themis tool [55], [76] randomly generates test inputs and checks whether the software system produces the same output for every two individuals who differ only in sensitive attribute values. Similarly, Aequitas [78] and ExpGA [77] search the input space of the software for discriminatory instances that reveal unfair predictions.…”

Section: Algorithm Testingmentioning

confidence: 99%

“…Usage scenario Description Link FairTest [140] General ML software Analyzing associations between software outcomes and sensitive attributes [196] Themis [55] General ML software Black-box random discriminatory instance generation [197] Aequitas [78] General ML software Black-box search-based discriminatory instance generation [198] ExpGA [77] General ML software Black-box search-based discriminatory instance generation [199] fairCheck [89] General ML software Verification-based discriminatory instance generation [200] MLCheck [88] General ML software Verification-based discriminatory instance generation [201] LTDD [50] General ML software Detecting which data features and which parts of them are biased [202] Fair-SMOTE [48] General ML software Detecting biased data labels and data distributions [203] xFAIR [144] General ML software Extrapolation of correlations among data features that might cause bias [204] Fairway [35] General ML software Detecting biased data labels and optimal hyper-parameters for ML fairness [205] Parfait-ML [46] General ML software Searching for hyper-parameters optimal to ML software fairness [206] Fairea [38] General ML software Testing fairness repair algorithms [207] IBM AIF360 [161] General ML software Examining and mitigating discrimination and bias in ML software [119] scikit-fairness [208] General ML software Examining and mitigating discrimination and bias in ML software [208] LiFT [209] General ML software Examining and mitigating discrimination and bias in ML software [210] SageMaker Clarify [211] General ML software Measuring bias that occurs in each stage of the ML life cycle [212] FairVis [213] General ML software Visual analytics for discovering intersectional bias in ML software [214] FairRepair [155] Tree-based classifiers Detecting paths responsible for unfairness in tree-based classifiers [215] ADF…”

Section: Tool [Ref]mentioning

confidence: 99%

See 2 more Smart Citations

Fairness Testing: A Comprehensive Survey and Analysis of Trends

Chen¹,

Zhang²,

Hort³

et al. 2022

Preprint

View full text Add to dashboard Cite

Software systems are vulnerable to fairness bugs and frequently exhibit unfair behaviors, making software fairness an increasingly important concern for software engineers. Research has focused on helping software engineers to detect fairness bugs automatically. This paper provides a comprehensive survey of existing research on fairness testing. We collect 113 papers and organise them based on the testing workflow (i.e., the testing activities) and the testing components (i.e., where to find fairness bugs) for conducting fairness testing. We also analyze the research focus, trends, promising directions, as well as widely-adopted datasets and open source tools for fairness testing.

show abstract