{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:19:20Z","timestamp":1763018360077,"version":"build-2065373602"},"reference-count":56,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T00:00:00Z","timestamp":1615680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The widespread use of automated decision processes in many areas of our society raises serious ethical issues with respect to the fairness of the process and the possible resulting discrimination. To solve this issue, we propose a novel adversarial training approach called GANSan for learning a sanitizer whose objective is to prevent the possibility of any discrimination (i.e., direct and indirect) based on a sensitive attribute by removing the attribute itself as well as the existing correlations with the remaining attributes. Our method GANSan is partially inspired by the powerful framework of generative adversarial networks (in particular Cycle-GANs), which offers a flexible way to learn a distribution empirically or to translate between two different distributions. In contrast to prior work, one of the strengths of our approach is that the sanitization is performed in the same space as the original data by only modifying the other attributes as little as possible, thus preserving the interpretability of the sanitized data. Consequently, once the sanitizer is trained, it can be applied to new data locally by an individual on their profile before releasing it. Finally, experiments on real datasets demonstrate the effectiveness of the approach as well as the achievable trade-off between fairness and utility.<\/jats:p>","DOI":"10.3390\/a14030087","type":"journal-article","created":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T22:13:10Z","timestamp":1615759990000},"page":"87","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Local Data Debiasing for Fairness Based on Generative Adversarial Training"],"prefix":"10.3390","volume":"14","author":[{"given":"Ulrich","family":"A\u00efvodji","sequence":"first","affiliation":[{"name":"D\u00e9partment d\u2019Informatique, Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montreal, QC H2L 2C4, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9813-0388","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Bidet","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Informatique de l\u2019\u00c9cole polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France"}]},{"given":"S\u00e9bastien","family":"Gambs","sequence":"additional","affiliation":[{"name":"D\u00e9partment d\u2019Informatique, Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montreal, QC H2L 2C4, Canada"}]},{"given":"Rosin Claude","family":"Ngueveu","sequence":"additional","affiliation":[{"name":"D\u00e9partment d\u2019Informatique, Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montreal, QC H2L 2C4, Canada"}]},{"given":"Alain","family":"Tapp","sequence":"additional","affiliation":[{"name":"DIRO, Universit\u00e9 de Montr\u00e9al, Montreal, QC H3T 1J4, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2021,3,14]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Mahmoud, M., Algadi, N., and Ali, A. (September, January 29). Expert System for Banking Credit Decision. Proceedings of the 2008 International Conference on Computer Science and Information Technology, Singapore.","key":"ref_1","DOI":"10.1109\/ICCSIT.2008.31"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1108\/10662241211271545","article-title":"An integrated e-recruitment system for automated personality mining and applicant ranking","volume":"22","author":"Faliagka","year":"2012","journal-title":"Internet Res."},{"unstructured":"Electronic Privacy Information Center (2020, April 17). EPIC-Algorithms in the Criminal Justice System. Available online: https:\/\/epic.org\/foia\/doj\/criminal-justice-algorithms.","key":"ref_3"},{"unstructured":"Angwin, J., Larson, J., Mattu, S., and Kirchner, L. (2020, April 17). Machine Bias. Available online: https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing.","key":"ref_4"},{"unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.","key":"ref_5"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1080\/01621459.1965.10480775","article-title":"Randomized response: A survey technique for eliminating evasive answer bias","volume":"60","author":"Warner","year":"1965","journal-title":"J. Am. Stat. Assoc."},{"doi-asserted-by":"crossref","unstructured":"Friedler, S.A., Scheidegger, C., Venkatasubramanian, S., Choudhary, S., Hamilton, E.P., and Roth, D. (2019, January 29\u201331). A comparative study of fairness-enhancing interventions in machine learning. Proceedings of the Conference on Fairness, Accountability, and Transparency, Atlanta, GA, USA.","key":"ref_7","DOI":"10.1145\/3287560.3287589"},{"doi-asserted-by":"crossref","unstructured":"Romanelli, M., Palamidessi, C., and Chatzikokolakis, K. (2019). Generating Optimal Privacy-Protection Mechanisms via Machine Learning. arXiv.","key":"ref_8","DOI":"10.1109\/CSF49147.2020.00019"},{"unstructured":"Kearns, M., Neel, S., Roth, A., and Wu, Z.S. (2017). Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. arXiv.","key":"ref_9"},{"doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., and Shmatikov, V. (2017, January 22\u201326). Membership inference attacks against machine learning models. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.","key":"ref_10","DOI":"10.1109\/SP.2017.41"},{"doi-asserted-by":"crossref","unstructured":"Song, L., Shokri, R., and Mittal, P. (2019, January 23). Membership inference attacks against adversarially robust deep learning models. Proceedings of the 2019 IEEE Security and Privacy Workshops (SPW), San Francisco, CA, USA.","key":"ref_11","DOI":"10.1109\/SPW.2019.00021"},{"doi-asserted-by":"crossref","unstructured":"Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., and Backes, M. (2018). Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models. arXiv.","key":"ref_12","DOI":"10.14722\/ndss.2019.23119"},{"unstructured":"Zhang, B., Yu, R., Sun, H., Li, Y., Xu, J., and Wang, H. (2020). Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack. arXiv.","key":"ref_13"},{"doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., and Zemel, R. (2012, January 8\u201310). Fairness through awareness. Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, Cambridge, MA, USA.","key":"ref_14","DOI":"10.1145\/2090236.2090255"},{"unstructured":"Joseph, M., Kearns, M., Morgenstern, J.H., and Roth, A. (2016, January 5\u201310). Fairness in learning: Classic and contextual bandits. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain.","key":"ref_15"},{"doi-asserted-by":"crossref","unstructured":"Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., and Huq, A. (2017, January 13\u201317). Algorithmic decision making and the cost of fairness. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada.","key":"ref_16","DOI":"10.1145\/3097983.3098095"},{"unstructured":"Narayanan, A. (2018, January 23\u201324). Translation tutorial: 21 fairness definitions and their politics. Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), New York, NY, USA.","key":"ref_17"},{"doi-asserted-by":"crossref","unstructured":"Verma, S., and Rubin, J. (2018, January 29). Fairness Definitions Explained. Proceedings of the 2018 IEEE\/ACM International Workshop on Software Fairness (FairWare), Gothenburg, Sweden.","key":"ref_18","DOI":"10.1145\/3194770.3194776"},{"key":"ref_19","first-page":"671","article-title":"Big data\u2019s disparate impact","volume":"104","author":"Barocas","year":"2016","journal-title":"Cal. L. Rev."},{"doi-asserted-by":"crossref","unstructured":"Berk, R., Heidari, H., Jabbari, S., Kearns, M., and Roth, A. (2018). Fairness in criminal justice risk assessments: The state of the art. Sociol. Methods Res., 0049124118782533.","key":"ref_20","DOI":"10.1177\/0049124118782533"},{"unstructured":"Hardt, M., Price, E., and Srebro, N. (2016, January 5\u201310). Equality of opportunity in supervised learning. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain.","key":"ref_21"},{"doi-asserted-by":"crossref","unstructured":"Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., and Venkatasubramanian, S. (2015, January 10\u201313). Certifying and removing disparate impact. Proceedings of the 21th ACM SIGKDD International Conference On Knowledge Discovery and Data Mining, Sydney, Australia.","key":"ref_22","DOI":"10.1145\/2783258.2783311"},{"doi-asserted-by":"crossref","unstructured":"Xu, D., Yuan, S., Zhang, L., and Wu, X. (2018). FairGan: Fairness-aware Generative Adversarial Networks. arXiv.","key":"ref_23","DOI":"10.1109\/BigData.2018.8622525"},{"unstructured":"Edwards, H., and Storkey, A. (2015). Censoring representations with an adversary. arXiv.","key":"ref_24"},{"unstructured":"Louizos, C., Swersky, K., Li, Y., Welling, M., and Zemel, R. (2015). The variational fair autoencoder. arXiv.","key":"ref_25"},{"unstructured":"Zemel, R., Wu, Y., Swersky, K., Pitassi, T., and Dwork, C. (2013, January 16\u201321). Learning fair representations. Proceedings of the International Conference on Machine Learning, Atlanta, GA, USA.","key":"ref_26"},{"unstructured":"Zafar, M.B., Valera, I., Rogriguez, M.G., and Gummadi, K.P. (2017, January 20\u201322). Fairness constraints: Mechanisms for fair classification. Proceedings of the Artificial Intelligence and Statistics, PMLR, Fort Lauderdale, FL, USA.","key":"ref_27"},{"doi-asserted-by":"crossref","unstructured":"Kamishima, T., Akaho, S., Asoh, H., and Sakuma, J. (2012, January 19\u201323). Fairness-aware classifier with prejudice remover regularizer. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Athens, Greece.","key":"ref_28","DOI":"10.1007\/978-3-642-33486-3_3"},{"doi-asserted-by":"crossref","unstructured":"Kamiran, F., Calders, T., and Pechenizkiy, M. (2010, January 13\u201317). Discrimination Aware Decision Tree Learning. Proceedings of the 2010 IEEE International Conference on Data Mining, ICDM \u201910, Sydney, Australia.","key":"ref_29","DOI":"10.1109\/ICDM.2010.50"},{"unstructured":"Kingma, D.P., and Welling, M. (2013, January 2\u20134). Auto-encoding variational bayes. Proceedings of the 2nd International Conference on Learning Representations (ICLR), Scottsdale, AZ, USA.","key":"ref_30"},{"doi-asserted-by":"crossref","unstructured":"Gretton, A., Borgwardt, K.M., Rasch, M., Sch\u00f6lkopf, B., and Smola, A.J. (2007, January 3\u20136). A kernel method for the two-sample-problem. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.","key":"ref_31","DOI":"10.7551\/mitpress\/7503.003.0069"},{"unstructured":"Creager, E., Madras, D., Jacobsen, J.H., Weis, M.A., Swersky, K., Pitassi, T., and Zemel, R. (2019). Flexibly fair representation learning by disentanglement. arXiv.","key":"ref_32"},{"doi-asserted-by":"crossref","unstructured":"Jha, A.H., Anand, S., Singh, M., and Veeravasarapu, V. (2018, January 8\u201314). Disentangling factors of variation with cycle-consistent variational auto-encoders. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","key":"ref_33","DOI":"10.1007\/978-3-030-01219-9_49"},{"unstructured":"Madras, D., Creager, E., Pitassi, T., and Zemel, R. (2018). Learning adversarially fair and transferable representations. arXiv.","key":"ref_34"},{"unstructured":"Beutel, A., Chen, J., Zhao, Z., and Chi, E.H. (2017). Data decisions and theoretical implications when adversarially learning fair representations. arXiv.","key":"ref_35"},{"doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., and Mitchell, M. (2018, January 2\u20133). Mitigating Unwanted Biases with Adversarial Learning. Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, New Orleans, LA, USA.","key":"ref_36","DOI":"10.1145\/3278721.3278779"},{"unstructured":"Wadsworth, C., Vera, F., and Piech, C. (2018). Achieving Fairness through Adversarial Learning: An Application to Recidivism Prediction. arXiv.","key":"ref_37"},{"unstructured":"Sattigeri, P., Hoffman, S.C., Chenthamarakshan, V., and Varshney, K.R. (2018). Fairness GAN. arXiv.","key":"ref_38"},{"doi-asserted-by":"crossref","unstructured":"McNamara, D., Ong, C.S., and Williamson, R.C. (2019, January 27\u201328). Costs and benefits of fair representation learning. Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, Honolulu, HI, USA.","key":"ref_39","DOI":"10.1145\/3306618.3317964"},{"doi-asserted-by":"crossref","unstructured":"Xu, D., Yuan, S., Zhang, L., and Wu, X. (2019, January 9\u201312). FairGan+: Achieving fair data generation and classification through generative adversarial nets. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","key":"ref_40","DOI":"10.1109\/BigData47090.2019.9006322"},{"unstructured":"Calmon, F., Wei, D., Vinzamuri, B., Ramamurthy, K.N., and Varshney, K.R. (2017, January 4\u20139). Optimized pre-processing for discrimination prevention. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.","key":"ref_41"},{"unstructured":"Feutry, C., Piantanida, P., Bengio, Y., and Duhamel, P. (2018). Learning anonymized representations with adversarial neural networks. arXiv.","key":"ref_42"},{"doi-asserted-by":"crossref","unstructured":"Pittaluga, F., Koppal, S., and Chakrabarti, A. (2019, January 7\u201311). Learning privacy preserving encodings through adversarial training. Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA.","key":"ref_43","DOI":"10.1109\/WACV.2019.00089"},{"unstructured":"Tripathy, A., Wang, Y., and Ishwar, P. (2017). Privacy-preserving adversarial networks. arXiv.","key":"ref_44"},{"unstructured":"Wang, Y., Wu, X., and Hu, D. (2016, January 15\u201318). Using Randomized Response for Differential Privacy Preserving Data Collection. Proceedings of the EDBT\/ICDT Workshops, Bordeaux, France.","key":"ref_45"},{"doi-asserted-by":"crossref","unstructured":"Du, W., and Zhan, Z. (2003, January 24\u201327). Using randomized response techniques for privacy-preserving data mining. Proceedings of the Ninth ACM SIGKDD International Conference On Knowledge Discovery and Data Mining, Washington, DC, USA.","key":"ref_46","DOI":"10.1145\/956750.956810"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"4505","DOI":"10.1109\/JIOT.2020.2967734","article-title":"A hybrid deep learning architecture for privacy-preserving mobile analytics","volume":"7","author":"Osia","year":"2020","journal-title":"IEEE Internet Things J."},{"unstructured":"Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.","key":"ref_48"},{"doi-asserted-by":"crossref","unstructured":"Kamiran, F., and Calders, T. (2009, January 17\u201318). Classifying without discriminating. Proceedings of the 2009 2nd International Conference on Computer, Control and Communication, Karachi, Pakistan.","key":"ref_49","DOI":"10.1109\/IC4.2009.4909197"},{"unstructured":"Dirac, P.A.M. (1981). The Principles of Quantum Mechanics, Oxford University Press. Number 27.","key":"ref_50"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_52","first-page":"579","article-title":"Multilayer perceptron and neural networks","volume":"8","author":"Popescu","year":"2009","journal-title":"WSEAS Trans. Circuits Syst."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","article-title":"Stochastic gradient boosting","volume":"38","author":"Friedman","year":"2002","journal-title":"Comput. Stat. Data Anal."},{"unstructured":"Bellamy, R.K., Dey, K., Hind, M., Hoffman, S.C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., and Mojsilovic, A. (2018). AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv.","key":"ref_54"},{"unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2017, January 4\u20139). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the 32nd Annual Conference on Neural Information Processing Systems 2019 (NeurIPS 2019), Vancouver, BC, Canada.","key":"ref_55"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"012001","DOI":"10.1088\/1742-6596\/341\/1\/012001","article-title":"Compute Canada: Advancing computational research","volume":"341","author":"Baldwin","year":"2012","journal-title":"J. Phys. Conf. Ser."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/3\/87\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:35:34Z","timestamp":1760160934000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/3\/87"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,14]]},"references-count":56,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["a14030087"],"URL":"https:\/\/doi.org\/10.3390\/a14030087","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2021,3,14]]}}}