Fairness Testing

Target Conference:

International Workshop on Combinatorial Testing (IWCT 2025)

Summary:

Decision-making by Machine Learning (ML) models can exhibit biased behavior, resulting in unfair outcomes.
Testing ML models for such biases is essential to ensure unbiased decision-making.
In this work, we propose a combinatorial testing-based approach in the latent space of a generative model to generate instances that assess the fairness of black-box ML models.
Our approach involves a two-step process: generating t-way test cases in the latent space of a Variational AutoEncoder and performing fairness testing using the instances reconstructed from these test cases.

Relevant Papers:

  1. Chen, Zhenpeng, et al. "Fairness testing: A comprehensive survey and analysis of trends." ACM Transactions on Software Engineering and Methodology 33.5 (2024): 1-59.
  2. Xiao, Yisong, et al. "Latent imitator: Generating natural individual discriminatory instances for black-box fairness testing." Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis. 2023.
  3. Aggarwal, Aniya, et al. "Black box fairness testing of machine learning models." Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2019.
  4. Wang, Zhaohui, et al. "MAFT: Efficient Model-Agnostic Fairness Testing for Deep Neural Networks via Zero-Order Gradient Search." Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. 2024.
  5. Khadka, Krishna, et al. "Synthetic data generation using combinatorial testing and variational autoencoder." 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). IEEE, 2023.
  6. Patel, Ankita Ramjibhai, et al. "A combinatorial approach to fairness testing of machine learning models." 2022 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). IEEE, 2022.
  7. Kacker, Raghu N., et al. "Factorials experiments, covering arrays, and combinatorial testing." Mathematics in Computer Science 15 (2021): 715-739.
  8. Lei, Yu, et al. "IPOG: A general strategy for t-way software testing." 14th Annual IEEE International Conference and Workshops on the Engineering of Computer-Based Systems (ECBS'07). IEEE, 2007.
  9. Bellamy, Rachel KE, et al. "AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias." IBM Journal of Research and Development 63.4/5 (2019): 4-1.
  10. Mothilal, Ramaravind K., Amit Sharma, and Chenhao Tan. "Explaining machine learning classifiers through diverse counterfactual explanations." Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. 2020.
  11. Udeshi, Sakshi, Pryanshu Arora, and Sudipta Chattopadhyay. "Automated directed fairness testing." Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering. 2018.
  12. Kingma, Diederik P., and Max Welling. "An introduction to variational autoencoders." Foundations and Trends® in Machine Learning 12.4 (2019): 307-392.
  13. Fayyad, Usama M., and Keki B. Irani. "Multi-interval discretization of continuous-valued attributes for classification learning." IJCAI. Vol. 93. No. 2. 1993.
  14. Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. "Model-agnostic interpretability of machine learning." arXiv preprint arXiv:1606.05386 (2016).
  15. Jiang, Weipeng, et al. "Black-Box Fairness Testing with Shadow Models." International Conference on Information and Communications Security. Singapore: Springer Nature Singapore, 2023.
  16. Fan, Ming, et al. "Explanation-guided fairness testing through genetic algorithm." Proceedings of the 44th International Conference on Software Engineering. 2022.
  17. Zheng, Haibin, et al. "Neuronfair: Interpretable white-box fairness testing through biased neuron identification." Proceedings of the 44th International Conference on Software Engineering. 2022.
  18. Galhotra, Sainyam, Yuriy Brun, and Alexandra Meliou. "Fairness testing: Testing software for discrimination." Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering. 2017.
  19. Perez Morales, Daniel, Takashi Kitamura, and Shingo Takada. "Coverage-guided fairness testing." International Conference on Intelligence Science. Cham: Springer International Publishing, 2021.
  20. Kitamura, Takashi, Zhenjiang Zhao, and Takahisa Toda. "Applying combinatorial testing to verification-based fairness testing." International Symposium on Search Based Software Engineering. Cham: Springer International Publishing, 2022.
  21. Yin, Ziqiang, Wentian Zhao, and Tian Song. "Boundary-Guided Black-Box Fairness Testing." 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC). IEEE, 2024.
  22. Tao, Guanhong, et al. "RULER: Discriminative and iterative adversarial training for deep neural network fairness." Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2022.
  23. Shahani, Aarti. "Now algorithms are deciding whom to hire, based on voice." NPR All Things Considered (2015).
  24. Mickisch, David, et al. "Understanding the decision boundary of deep neural networks: An empirical study." arXiv preprint arXiv:2002.01810 (2020).
  25. Flores, Anthony W., Kristin Bechtel, and Christopher T. Lowenkamp. "False positives, false negatives, and false analyses: A rejoinder to machine bias: There's software used across the country to predict future criminals. And it's biased against blacks." Federal Probation 80 (2016): 38.
  26. John, Philips George, Deepak Vijaykeerthy, and Diptikalyan Saha. "Verifying individual fairness in machine learning models." Conference on Uncertainty in Artificial Intelligence. PMLR, 2020.
  27. Cabrera, Ángel Alexander, et al. "FairVis: Visual analytics for discovering intersectional bias in machine learning." 2019 IEEE Conference on Visual Analytics Science and Technology (VAST). IEEE, 2019.
  28. Monjezi, Verya, et al. "Information-theoretic testing and debugging of fairness defects in deep neural networks." 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE). IEEE, 2023.
  29. Zhang, Peixin, et al. "White-box fairness testing through adversarial sampling." Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering. 2020.
  30. Liu, Zeyuan, Xin Zhang, and Benben Jiang. "Active learning with fairness-aware clustering for fair classification considering multiple sensitive attributes." Information Sciences 647 (2023): 119521.
  31. Haffar, Rami, et al. "Measuring fairness in machine learning models via counterfactual examples." International Conference on Modeling Decisions for Artificial Intelligence. Cham: Springer International Publishing, 2022.
  32. Dash, Saloni, Vineeth N. Balasubramanian, and Amit Sharma. "Evaluating and mitigating bias in image classifiers: A causal perspective using counterfactuals." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2022.
  33. Vassøy, Bjørnar, Helge Langseth, and Benjamin Kille. "Providing previously unseen users fair recommendations using variational autoencoders." Proceedings of the 17th ACM Conference on Recommender Systems. 2023.
  34. Louizos, Christos, et al. "The variational fair autoencoder." arXiv preprint arXiv:1511.00830 (2015).
  35. Panagiotou, Emmanouil, Arjun Roy, and Eirini Ntoutsi. "Synthetic tabular data generation for class imbalance and fairness: A comparative study." arXiv preprint arXiv:2409.05215 (2024).