{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:15:16Z","timestamp":1783782916656,"version":"3.55.0"},"reference-count":84,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T00:00:00Z","timestamp":1783728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62372084"],"award-info":[{"award-number":["62372084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100014013","name":"UKRI","doi-asserted-by":"crossref","award":["10054084"],"award-info":[{"award-number":["10054084"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:p>\n                    To mitigate unfair and unethical discrimination over sensitive features (e.g., gender, age, or race), fairness testing plays an integral role in engineering systems that leverage AI models to handle tabular data. A key challenge therein is how to effectively reveal fairness bugs under an intractable sample size using perturbation. Much current work has been focusing on designing the test sample generators, ignoring the valuable knowledge about data characteristics that can help guide the perturbation and hence limiting their full potential. In this article, we seek to bridge such a gap by proposing a generic framework of causally perturbed fairness testing, dubbed\n                    <jats:monospace>CausalFT<\/jats:monospace>\n                    . Through causal inference, the key idea of\n                    <jats:monospace>CausalFT<\/jats:monospace>\n                    is to extract the most directly and causally relevant non-sensitive feature to its sensitive counterpart, which can jointly influence the prediction of the label. Such a causal relationship is then seamlessly injected into the perturbation to guide a test sample generator. Unlike existing generator-level work,\n                    <jats:monospace>CausalFT<\/jats:monospace>\n                    serves as a higher-level framework that can be paired with diverse base generators. Extensive experiments on 1,296 cases confirm that\n                    <jats:monospace>CausalFT<\/jats:monospace>\n                    can considerably improve arbitrary base generators in revealing fairness bugs over 93% of the cases with acceptable extra run-time overhead. Compared with a state-of-the-art approach that ranks the non-sensitive features solely based on correlation,\n                    <jats:monospace>CausalFT<\/jats:monospace>\n                    performs significantly better on 64% cases while being much more efficient. Further,\n                    <jats:monospace>CausalFT<\/jats:monospace>\n                    can better improve bias resilience in nearly all cases.\n                  <\/jats:p>","DOI":"10.1145\/3773088","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T14:48:01Z","timestamp":1761576481000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Causally Perturbed Fairness Testing"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6715-5375","authenticated-orcid":false,"given":"Chengwen","family":"Du","sequence":"first","affiliation":[{"name":"IDEAS Lab, University of Birmingham, Birmingham, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5025-5472","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"IDEAS Lab, University of Birmingham, Birmingham, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,11]]},"reference":[{"key":"e_1_3_2_1_2","unstructured":"1994. The German Credit Dataset. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Statlog+%28German+Credit+ Data%29"},{"key":"e_1_3_2_2_2","unstructured":"1998. The Law School Dataset. Retrieved from https:\/\/www.kaggle.com\/datasets\/danofer\/law-school-admissions-bar-passage"},{"key":"e_1_3_2_3_2","unstructured":"2000. Census-Income (KDD). Retrieved from https:\/\/archive.ics.uci.edu\/dataset\/117\/census+income+kdd"},{"key":"e_1_3_2_4_2","unstructured":"2011. The Communities and Crime Dataset. Retrieved from http:\/\/archive.ics.uci.edu\/dataset\/211\/communities+and+ crime+unnormalized"},{"key":"e_1_3_2_5_2","unstructured":"2014. The Dutch Census of 2001 Dataset. Retrieved from https:\/\/microdata.worldbank.org\/index.php\/catalog\/2102"},{"key":"e_1_3_2_6_2","unstructured":"2016. The Compas Dataset. Retrieved May 20 2022 from https:\/\/github.com\/propublica\/compas-analysis"},{"key":"e_1_3_2_7_2","unstructured":"2016. The Default Credit Dataset. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/default+of+credit+card+clients"},{"key":"e_1_3_2_8_2","unstructured":"2017. The Adult Census Income Dataset. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/adult"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338937"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2001420.2001452"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1177\/0049124118782533"},{"key":"e_1_3_2_12_2","first-page":"149","volume-title":"Conference on Fairness, Accountability and Transparency (FAT \u201918)Proceedings of Machine Learning Research","author":"Binns Reuben","year":"2018","unstructured":"Reuben Binns. 2018. Fairness in machine learning: Lessons from political philosophy. In Conference on Fairness, Accountability and Transparency (FAT \u201918). Sorelle A. Friedler and Christo Wilson (Eds.), Proceedings of Machine Learning Research, Vol. 81, PMLR, 149\u2013159. Retrieved from http:\/\/proceedings.mlr.press\/v81\/binns18a.html"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372864"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409704"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/3272525.3272526"},{"key":"e_1_3_2_16_2","volume-title":"48th IEEE\/ACM International Conference on Software Engineering (ICSE)","author":"Chen Pengzhou","year":"2026","unstructured":"Pengzhou Chen and Tao Chen. 2026. PromiseTune: Unveiling causally promising and explainable configuration tuning. In 48th IEEE\/ACM International Conference on Software Engineering (ICSE). ACM."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3388910"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3525955"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00022"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468555"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514233"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643751"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652155"},{"key":"e_1_3_2_24_2","first-page":"507","article-title":"Optimal structure identification with greedy search","volume":"3","author":"Chickering David Maxwell","year":"2002","unstructured":"David Maxwell Chickering. 2002. Optimal structure identification with greedy search. J. Mach. Learn. Res 3 (2002), 507\u2013554. Retrieved from https:\/\/jmlr.org\/papers\/v3\/chickering02b.html","journal-title":"J. Mach. Learn. Res"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3674805.3686673"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.3000681"},{"key":"e_1_3_2_27_2","unstructured":"Jannik Dunkelau and Manh Khoi Duong. 2022. Towards equalised odds as fairness metric in academic performance prediction. arXiv:2209.14670. Retrieved from https:\/\/arxiv.org\/abs\/2209.14670"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"e_1_3_2_29_2","unstructured":"Ahmad-Reza Ehyaei Golnoosh Farnadi and Samira Samadi. 2023. Causal fair metric: Bridging causality individual fairness and adversarial robustness. arXiv:2310.19391. Retrieved from https:\/\/arxiv.org\/abs\/2310.19391"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.830118"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510137"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462621"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106277"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616334"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643743"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3491945"},{"key":"e_1_3_2_37_2","first-page":"3315","volume-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016. Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (Eds.), 3315\u20133323. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/9d2682367c3935defcb1f9e247a97c0d-Abstract.html"},{"key":"e_1_3_2_38_2","unstructured":"Zhenlan Ji Pingchuan Ma Shuai Wang and Yanhui Li. 2023. Causality-aided trade-off analysis for machine learning fairness. arXiv:2305.13057. Retrieved from https:\/\/arxiv.org\/abs\/2305.13057"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7356-9_28"},{"key":"e_1_3_2_40_2","volume-title":"The 10th International Conference on Learning Representations (ICLR \u201922)","author":"Jiang Zhimeng","year":"2022","unstructured":"Zhimeng Jiang, Xiaotian Han, Chao Fan, Fan Yang, Ali Mostafavi, and Xia Hu. 2022. Generalized demographic parity for group fairness. In The 10th International Conference on Learning Representations (ICLR \u201922). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=YigKlMJwjye"},{"key":"e_1_3_2_41_2","unstructured":"Brian Hyeongseok Kim Jingbo Wang and Chao Wang. 2024. FairQuant: Certifying and quantifying fairness of deep neural networks. arXiv:2409.03220. Retrieved from https:\/\/arxiv.org\/abs\/2409.03220"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/S18-2005"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00121"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3036108"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462966"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3122443"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643890"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533171"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00136"},{"key":"e_1_3_2_51_2","unstructured":"Carlos Mougan Laura State Antonio Ferrara Salvatore Ruggieri and Steffen Staab. 2023. Demographic parity inspector: Fairness audits via the explanation space. arXiv:2303.08040. Retrieved from https:\/\/arxiv.org\/abs\/2303.08040"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax2342"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401959"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1002\/WIDM.1452"},{"key":"e_1_3_2_55_2","first-page":"6414","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Russell Chris","year":"2017","unstructured":"Chris Russell, Matt J. Kusner, Joshua R. Loftus, and Ricardo Silva. 2017. When worlds collide: Integrating different counterfactual assumptions in fairness. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017. Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.), 6414\u20136423. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/1271a7029c9df08643b631b02cf9e116-Abstract.html"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248619"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021040"},{"key":"e_1_3_2_58_2","unstructured":"Ricardo Silva. 2024. Counterfactual fairness is not demographic parity and other observations. arXiv:2402.02663. Retrieved from https:\/\/doi.org\/10.48550\/ARXIV.2402.02663"},{"key":"e_1_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Edward A. Small Kacper Sokol Daniel Manning Flora D. Salim and Jeffrey Chan. 2023. Equalised odds is not equal individual odds: Post-processing for group and individual fairness. arXiv:2304.09779. Retrieved from https:\/\/arxiv.org\/abs\/2304.09779","DOI":"10.1145\/3630106.3658989"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632529"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510202"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2017.29"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238165"},{"key":"e_1_3_2_64_2","first-page":"101","article-title":"A critique and improvement of the CL common language effect size statistics of McGraw and wong","volume":"25","author":"Vargha Andr\u00e1s","year":"2000","unstructured":"Andr\u00e1s Vargha and Harold D. Delaney. 2000. A critique and improvement of the CL common language effect size statistics of McGraw and wong. J. Educ. Behav. Stat. 25 (2000), 101\u2013132. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:120137017","journal-title":"J. Educ. Behav. Stat"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"e_1_3_2_66_2","first-page":"3399","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 (NeurIPS \u201919)","author":"Wu Yongkai","year":"2019","unstructured":"Yongkai Wu, Lu Zhang, Xintao Wu, and Hanghang Tong. 2019. PC-Fairness: A unified framework for measuring causality-based fairness. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019 (NeurIPS \u201919). Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d\u2019Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.), 3399\u20133409. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/44a2e0804995faf8d2e3b084a1e2db1d-Abstract.html"},{"key":"e_1_3_2_67_2","volume-title":"48th IEEE\/ACM International Conference on Software Engineering (ICSE)","author":"Xiang Zezhen","year":"2026","unstructured":"Zezhen Xiang, Jingzhi Gong, and Tao Chen. 2026. Dually hierarchical drift adaptation for online configuration performance learning. In 48th IEEE\/ACM International Conference on Software Engineering (ICSE). ACM."},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598099"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE63991.2025.00126"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.24963\/IJCAI.2019\/201"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411980"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00094"},{"key":"e_1_3_2_73_2","first-page":"962","volume-title":"20th International Conference on Artificial Intelligence and Statistics (AISTATS \u201917)Proceedings of Machine Learning Research","author":"Zafar Muhammad Bilal","year":"2017","unstructured":"Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez-Rodriguez, and Krishna P. Gummadi. 2017. Fairness constraints: Mechanisms for fair classification. In 20th International Conference on Artificial Intelligence and Statistics (AISTATS \u201917). Aarti Singh and Xiaojin (Jerry) Zhu (Eds.), Proceedings of Machine Learning Research, Vol. 54, PMLR, 962\u2013970. Retrieved from http:\/\/proceedings.mlr.press\/v54\/zafar17a.html"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"e_1_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Dacao Zhang Kun Zhang Le Wu Mi Tian Richang Hong and Meng Wang. 2024. Path-specific causal reasoning for fairness-aware cognitive diagnosis. arXiv:2406.03064. Retrieved from https:\/\/arxiv.org\/abs\/2406.03064","DOI":"10.1145\/3637528.3672049"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00129"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464820"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549103"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380331"},{"key":"e_1_3_2_80_2","unstructured":"Tianxiang Zhao Enyan Dai Kai Shu and Suhang Wang. 2021. You can still achieve fairness without sensitive attributes: Exploring biases in non-sensitive features. arXiv:2104.14537. Retrieved from https:\/\/arxiv.org\/abs\/2104.14537"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498493"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/BIGDATA59044.2023.10386836"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510123"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUCOM.2023.126841"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3773088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:04:06Z","timestamp":1783782246000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,11]]},"references-count":84,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3773088"],"URL":"https:\/\/doi.org\/10.1145\/3773088","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,11]]},"assertion":[{"value":"2025-03-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}