{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T22:41:40Z","timestamp":1793313700158,"version":"4.5.0"},"reference-count":96,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1934494"],"award-info":[{"award-number":["1934494"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1934925"],"award-info":[{"award-number":["1934925"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Concerns about the trustworthiness, fairness, and privacy of AI systems are growing, and strategies for mitigating these concerns are still in their infancy. One approach to improve trustworthiness and fairness in AI systems is to use bias mitigation algorithms. However, most bias mitigation algorithms require data sets that contain sensitive attribute values to assess the fairness of the algorithm. A growing number of real world data sets do not make sensitive attribute information readily available to researchers. One solution is to infer the missing sensitive attribute information and apply an existing bias mitigation algorithm using this inferred knowledge. While researchers are beginning to explore this question, it is still unclear how robust existing bias mitigation algorithms are to different levels of inference accuracy. This paper explores this question by investigating the impact of different levels of accuracy of the inferred sensitive attribute on the performance of different bias mitigation strategies. We generate variation in sensitive attribute accuracy using both simulation and construction of neural models for the inference task. We then assess the quality of six bias mitigation algorithms that are deployed across different parts of our learning life cycle: pre-processing, in-processing, and post-processing. We find that the disparate impact remover is the least sensitive bias mitigation strategy and that if we apply the bias mitigation algorithms using an inferred sensitive attribute with reasonable accuracy, the fairness scores are higher than the best standard model and the balanced accuracy is similar to that of the standard model. These findings open the door for improving fairness of black box AI systems using some bias mitigation strategies.<\/jats:p>","DOI":"10.3389\/frai.2025.1520330","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T14:17:27Z","timestamp":1741270647000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Impact on bias mitigation algorithms to variations in inferred sensitive attribute uncertainty"],"prefix":"10.3389","volume":"8","author":[{"given":"Yanchen","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,3,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1111\/1475-6773.12089","article-title":"Using the bayesian improved surname geocoding method (BISG) to create a working classification of race and ethnicity in a diverse managed care population: a validation study","volume":"49","author":"Adjaye-Gbewonyo","year":"2014","journal-title":"Health Serv. Res"},{"key":"B2","first-page":"60","article-title":"\u201cA reductions approach to fair classification,\u201d","volume-title":"Conference on Machine Learning","author":"Agarwal","year":"2018"},{"key":"B3","unstructured":"Andriotis\n              A.\n            \n            \n              Ensign\n              R. L.\n            \n          \n          U.S. Government Uses Race Test for $80 Million in Payments\n          \n          2015"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1017\/S0003055423000229","article-title":"Misclassification and bias in predictions of individual ethnicity from administrative records","volume":"118","author":"Argyle","year":"2024","journal-title":"Am. Polit. Sci. Rev"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445884","article-title":"\u201cEvaluating fairness of machine learning models under uncertain and incomplete information,\u201d","author":"Awasthi","year":"2021","journal-title":"ACM conference on Fairness, Accountability, and Transparency"},{"key":"B6","first-page":"1770","article-title":"\u201cEqualized odds postprocessing under imperfect group information,\u201d","volume-title":"Conference on Artificial Intelligence and Statistics","author":"Awasthi","year":"2020"},{"key":"B7","doi-asserted-by":"publisher","first-page":"671","DOI":"10.2139\/ssrn.2477899","article-title":"Big data's disparate impact","volume":"104","author":"Barocas","year":"2016","journal-title":"Calif. L. Rev"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3343038","article-title":"A survey on privacy in social media: identification, mitigation, and applications","volume":"1","author":"Beigi","year":"2020","journal-title":"ACM Trans. Data Sci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1147\/JRD.2019.2942287","article-title":"AI fairness 360: an extensible toolkit for detecting and mitigating algorithmic bias","volume":"63","author":"Bellamy","year":"2019","journal-title":"IBM J. Res. Dev"},{"key":"B10","article-title":"A convex framework for fair regression","author":"Berk","year":"2017","journal-title":"arXiv [Preprint]."},{"key":"B11","article-title":"Data decisions and theoretical implications when adversarially learning fair representations","author":"Beutel","year":"2017","journal-title":"arXiv [Preprint]."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.4324\/9781315263298","author":"Biddle","year":"2017","journal-title":"Adverse Impact and Test Validation: A Practitioner's Guide to Valid and Defensible Employment Testing"},{"key":"B13","author":"Bird","year":"2020","journal-title":"Fairlearn: a toolkit for assessing and improving fairness in AI"},{"key":"B14","first-page":"3121","article-title":"\u201cThe balanced accuracy and its posterior distribution,\u201d","volume-title":"Conference on Pattern Recognition","author":"Brodersen","year":"2010"},{"key":"B15","first-page":"803","article-title":"\u201cUnderstanding the origins of bias in word embeddings,\u201d","volume-title":"Conference on Machine Learning","author":"Brunet","year":"2019"},{"key":"B16","first-page":"77","article-title":"\u201cGender shades: intersectional accuracy disparities in commercial gender classification,\u201d","volume-title":"Conference on Fairness, Accountability and Transparency","author":"Buolamwini","year":"2018"},{"key":"B17","author":"Bureau","year":"2014","journal-title":"Using publicly available information to proxy for unidentified race and ethnicity"},{"key":"B18","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s10618-010-0190-x","article-title":"Three naive bayes approaches for discrimination-free classification","volume":"21","author":"Calders","year":"2010","journal-title":"Data Min. Knowl. Discov"},{"key":"B19","first-page":"3995","article-title":"\u201cOptimized pre-processing for discrimination prevention,\u201d","author":"Calmon","year":"2017","journal-title":"Conference on Neural Information Processing Systems"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468537","article-title":"\u201cBias in machine learning software: why? how? what to do?\u201d","author":"Chakraborty","year":"2021","journal-title":"Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287594","article-title":"\u201cFairness under unawareness: assessing disparity when protected class is unobserved,\u201d","author":"Chen","year":"2019","journal-title":"Conference on Fairness, Accountability, and Transparency"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v9i1.14656","article-title":"\u201cA comparative study of demographic attribute inference in twitter,\u201d","author":"Chen","year":"2015","journal-title":"International AAAI Conference on Web and Social Media"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549093","article-title":"\u201cMaat: a novel ensemble approach to addressing fairness and performance bugs for machine learning software,\u201d","author":"Chen","year":"2022","journal-title":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1145\/3597503.3639083","article-title":"\u201cFairness improvement with multiple protected attributes: how far are we?\u201d","volume-title":"ICSE '24: Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering","author":"Chen","year":"2024"},{"key":"B25","doi-asserted-by":"crossref","first-page":"103","DOI":"10.3115\/v1\/W14-4012","article-title":"\u201cOn the properties of neural machine translation: encoder-decoder approaches,\u201d","volume-title":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","author":"Cho","year":"2014"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9204","article-title":"\u201cPredicting the demographics of twitter users from website traffic data,\u201d","author":"Culotta","year":"2015","journal-title":"Conference on Artificial Intelligence"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372878","article-title":"\u201cFairness is not static: deeper understanding of long term fairness via simulation studies,\u201d","author":"D'Amour","year":"2020","journal-title":"Conference on Fairness, Accountability, and Transparency"},{"key":"B28","unstructured":"Dua\n              D.\n            \n            \n              Graff\n              C.\n            \n          \n          UCI Machine Learning Repository\n          \n          2017"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255","article-title":"\u201cFairness through awareness,\u201d","author":"Dwork","year":"2012","journal-title":"Innovations in Theoretical Computer Science Conference"},{"key":"B30","article-title":"Censoring representations with an adversary","author":"Edwards","year":"2015","journal-title":"arXiv [Preprint]."},{"key":"B31","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s10742-009-0047-1","article-title":"Using the census bureau's surname list to improve estimates of race\/ethnicity and associated disparities","volume":"9","author":"Elliott","year":"2009","journal-title":"Health Serv. Outc. Res. Methodol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311","article-title":"\u201cCertifying and removing disparate impact,\u201d","author":"Feldman","year":"2015","journal-title":"Conference on Knowledge Discovery and Data Mining"},{"key":"B33","first-page":"1918","article-title":"\u201cAn intersectional definition of fairness,\u201d","volume-title":"Conference on Data Engineering","author":"Foulds","year":"2020"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462850","article-title":"\u201cWhen fair ranking meets uncertain inference,\u201d","author":"Ghosh","year":"","journal-title":"Conference on Research and Development in Information Retrieval"},{"key":"B35","first-page":"22","article-title":"\u201cCharacterizing intersectional group fairness with worst-case comparisons,\u201d","volume-title":"Artificial Intelligence Diversity, Belonging, Equity, and Inclusion","author":"Ghosh","year":""},{"key":"B36","first-page":"3193","article-title":"\u201cLow-degree multicalibration,\u201d","volume-title":"Conference on Learning Theory","author":"Gopalan","year":"2022"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1136\/bmjqs-2012-001615","article-title":"The incidence of diagnostic error in medicine","author":"Graber","year":"2013","journal-title":"BMJ Qual. Safety"},{"key":"B38","article-title":"Fairness without the sensitive attribute via causal variational autoencoder","author":"Grari","year":"2021","journal-title":"arXiv:2109.04999."},{"key":"B39","article-title":"Proxy fairness","author":"Gupta","year":"2018","journal-title":"arXiv:1806.11212"},{"key":"B40","article-title":"\u201cEquality of opportunity in supervised learning,\u201d","author":"Hardt","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B41","first-page":"1929","article-title":"\u201cFairness without demographics in repeated loss minimization,\u201d","volume-title":"Conference on Machine Learning","author":"Hashimoto","year":"2018"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830","article-title":"\u201cImproving fairness in machine learning systems: what do industry practitioners need?\u201d","author":"Holstein","year":"2019","journal-title":"CHI Conference on Human Factors in Computing Systems"},{"key":"B43","first-page":"1","article-title":"\u201cPrivacy-preserving fair machine learning without collecting sensitive demographic data,\u201d","volume-title":"International Joint Conference on Neural Networks","author":"Hu","year":"2021"},{"key":"B44","unstructured":"Jeff\n              L.\n            \n            \n              Surya Mattu\n              L. K.\n            \n            \n              Angwin\n              J.\n            \n          \n          37190449\n          How We Analyzed the Compas Recidivism Algorithm\n          \n          2016"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","article-title":"Data preprocessing techniques for classification without discrimination","volume":"33","author":"Kamiran","year":"2012","journal-title":"Knowl. Inf. Syst"},{"key":"B46","first-page":"924","article-title":"\u201cDecision theory for discrimination-aware classification,\u201d","volume-title":"Conference on Data Mining","author":"Kamiran","year":"2012"},{"key":"B47","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/978-3-642-33486-3_3","article-title":"\u201cFairness-aware classifier with prejudice remover regularizer,\u201d","volume-title":"Conference on Machine Learning and Knowledge Discovery in Databases","author":"Kamishima","year":"2012"},{"key":"B48","first-page":"1455","article-title":"\u201cInfofair: information-theoretic intersectional fairness,\u201d","volume-title":"International Conference on Big Data","author":"Kang","year":"2022"},{"key":"B49","first-page":"2564","article-title":"\u201cPreventing fairness gerrymandering: auditing and learning for subgroup fairness,\u201d","volume-title":"Conference on Machine Learning","author":"Kearns","year":"2018"},{"key":"B50","first-page":"2630","article-title":"\u201cBlind justice: fairness with encrypted sensitive attributes,\u201d","volume-title":"Conference on Machine Learning","author":"Kilbertus","year":"2018"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314287","article-title":"\u201cMultiaccuracy: black-box post-processing for fairness in classification,\u201d","author":"Kim","year":"2019","journal-title":"Conference on AI, Ethics, and Society"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186133","article-title":"\u201cAdaptive sensitive reweighting to mitigate bias in fairness-aware classification,\u201d","author":"Krasanakis","year":"2018","journal-title":"World Wide Web Conference"},{"key":"B53","first-page":"728","article-title":"\u201cFairness without demographics through adversarially reweighted learning,\u201d","author":"Lahoti","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00980","article-title":"\u201cRepair: removing representation bias by dataset resampling,\u201d","author":"Li","year":"2019","journal-title":"Conference on Computer Vision and Pattern Recognition"},{"key":"B55","article-title":"Fairness of chatgpt","author":"Li","year":"2023","journal-title":"arXiv [Preprint]."},{"key":"B56","unstructured":"Inferred age or gender on LinkedIn\n          \n          2022"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482055","article-title":"\u201cAge inference using a hierarchical attention neural network,\u201d","author":"Liu","year":"2021","journal-title":"Conference on Information &Knowledge Management"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570462","article-title":"\u201cCombining vs. transferring knowledge: investigating strategies for improving demographic inference in low resource settings,\u201d","author":"Liu","year":"2023","journal-title":"Conference on Web Search and Data Mining"},{"key":"B59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3673899","article-title":"Utilizing external knowledge to enhance location prediction for Twitter\/X users in low resource settings","volume":"10","author":"Liu","year":"2024","journal-title":"ACM Trans. Spat. Algor. Syst"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.5220\/0010559500480058","article-title":"\u201cA comparative analysis of classic and deep learning models for inferring gender and age of twitter users,\u201d","author":"Liu","year":"2021","journal-title":"Conference on Deep Learning Theory and Applications"},{"key":"B61","first-page":"1048","article-title":"\u201cSubgroup generalization and fairness of graph neural networks,\u201d","author":"Ma","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B62","article-title":"Fnnc: achieving fairness through neural networks","author":"Manisha","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B63","first-page":"509","article-title":"\u201cDebiasing community detection: the importance of lowly connected nodes,\u201d","volume-title":"Conference on Advances in Social Networks Analysis and Mining","author":"Mehrabi","year":"2019"},{"key":"B64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","article-title":"A survey on bias and fairness in machine learning","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput. Surv"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314277","article-title":"\u201cActive fairness in algorithmic decision making,\u201d","author":"Noriega-Campero","year":"2019","journal-title":"AAAI\/ACM Conference on AI, Ethics, and Society"},{"key":"B66","first-page":"600","article-title":"\u201cAddressing fairness in classification with a model-agnostic multi-objective algorithm,\u201d","volume-title":"Uncertainty in Artificial Intelligence","author":"Padh","year":"2021"},{"key":"B67","doi-asserted-by":"publisher","first-page":"2426","DOI":"10.1109\/TSE.2022.3220713","article-title":"Fairmask: better fairness via model-based rebalancing of protected attributes","volume":"49","author":"Peng","year":"2022","journal-title":"IEEE Trans. Softw. Eng"},{"key":"B68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3494672","article-title":"A review on fairness in machine learning","volume":"55","author":"Pessach","year":"2022","journal-title":"ACM Comput. Surv"},{"key":"B69","first-page":"1256","article-title":"\u201cGradient starvation: a learning proclivity in neural networks,\u201d","author":"Pezeshki","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B70","article-title":"\u201cOn fairness and calibration,\u201d","author":"Pleiss","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B71","article-title":"Sentence-BERT: sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019","journal-title":"arXiv [Preprint]"},{"key":"B72","first-page":"361","article-title":"\u201cAchieving equalized odds by resampling sensitive attributes,\u201d","author":"Romano","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B73","article-title":"What's in a name? Reducing bias in bios without access to protected attributes","author":"Romanov","year":"2019","journal-title":"arXiv:1904.05233."},{"key":"B74","first-page":"34121","article-title":"\u201cOn learning fairness and accuracy on multiple subgroups,\u201d","author":"Shui","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B75","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3390\/bdcc6030077","article-title":"We know you are living in Bali: Location prediction of twitter users using Bert language model","volume":"6","author":"Simanjuntak","year":"2022","journal-title":"Big Data Cogn. Comput"},{"key":"B76","first-page":"23","article-title":"Social media data-our ethical conundrum","volume":"43","author":"Singh","year":"2020","journal-title":"Bull. IEEE Comput. Soc. Tech. Comm. Datab. Eng"},{"key":"B77","first-page":"19339","article-title":"\u201cNo subclass left behind: Fine-grained robustness in coarse-grained classification problems,\u201d","author":"Sohoni","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B78","first-page":"2123","article-title":"\u201cFairness-aware class imbalanced learning on multiple subgroups,\u201d","volume-title":"Uncertainty in Artificial Intelligence","author":"Tarzanagh","year":"2023"},{"key":"B79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-019-1004-8","article-title":"Comparing different supervised machine learning algorithms for disease prediction","volume":"19","author":"Uddin","year":"2019","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"B80","doi-asserted-by":"publisher","first-page":"2023","DOI":"10.5555\/2789272.2886814","article-title":"Learning using privileged information: similarity control and knowledge transfer","volume":"16","author":"Vapnik","year":"2015","journal-title":"J. Mach. Learn. Res"},{"key":"B81","doi-asserted-by":"publisher","first-page":"530","DOI":"10.31235\/osf.io\/ustxg","article-title":"Fairer machine learning in the real world: mitigating discrimination without collecting sensitive data","volume":"4","author":"Veale","year":"2017","journal-title":"Big Data Soc"},{"key":"B82","article-title":"Achieving fairness through adversarial learning: an application to recidivism prediction","author":"Wadsworth","year":"2018","journal-title":"arXiv:1807.00199"},{"key":"B83","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/s41060-021-00259-z","article-title":"Analyzing the impact of missing values and selection bias on fairness","volume":"12","author":"Wang","year":"2021","journal-title":"Int. J. Data Sci. Anal"},{"key":"B84","doi-asserted-by":"publisher","DOI":"10.1145\/3617694.3623244","article-title":"\u201cMitigating demographic bias of machine learning models on social media,\u201d","author":"Wang","year":"2023","journal-title":"Conference on Equity and Access in Algorithms, Mechanisms, and Optimization"},{"key":"B85","article-title":"It is time to develop an auditing framework to promote value aware chatbots","author":"Wang","year":"2024","journal-title":"arXiv [Preprint]"},{"key":"B86","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313684","article-title":"\u201cDemographic inference and representative population estimates from multilingual social media data,\u201d","author":"Wang","year":"2019","journal-title":"The World Wide Web Conference"},{"key":"B87","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1613\/jair.1.14747","article-title":"Can fairness be automated? Guidelines and opportunities for fairness-aware automl","volume":"79","author":"Weerts","year":"2024","journal-title":"J. Artif. Intell. Res"},{"key":"B88","article-title":"The what-if tool: Interactive probing of machine learning models","author":"Wexler","year":"2019","journal-title":"arXiv:1907.04135"},{"key":"B89","article-title":"Fairness-aware classification: criterion, convexity, and bounds","author":"Wu","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B90","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/201","article-title":"\u201cAchieving causal fairness through generative adversarial networks,\u201d","author":"Xu","year":"2019","journal-title":"Conference on Artificial Intelligence"},{"key":"B91","first-page":"962","article-title":"\u201cFairness constraints: mechanisms for fair classification,\u201d","volume-title":"Artificial Intelligence and Statistics","author":"Zafar","year":"2017"},{"key":"B92","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779","article-title":"\u201cMitigating unwanted biases with adversarial learning,\u201d","author":"Zhang","year":"2018","journal-title":"Conference on AI, Ethics, and Society"},{"key":"B93","article-title":"Is chatGPT fair for recommendation? Evaluating fairness in large language model recommendation","author":"Zhang","year":"2023","journal-title":"arXiv:2305.07609."},{"key":"B94","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1287\/mnsc.2016.2579","article-title":"Assessing fair lending risks using race\/ethnicity proxies","volume":"64","author":"Zhang","year":"2018","journal-title":"Manage. Sci"},{"key":"B95","article-title":"You can still achieve fairness without sensitive attributes: Exploring biases in non-sensitive features","author":"Zhao","year":"2021","journal-title":"arXiv [Preprint]"},{"key":"B96","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498493","article-title":"\u201cTowards fair classifiers without sensitive attributes: exploring biases in related features,\u201d","author":"Zhao","year":"2022","journal-title":"Conference on Web Search and Data Mining"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1520330\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T14:17:41Z","timestamp":1741270661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1520330\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,6]]},"references-count":96,"alternative-id":["10.3389\/frai.2025.1520330"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1520330","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,6]]},"article-number":"1520330"}}