{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:05:19Z","timestamp":1775693119857,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000943","name":"Commonwealth Scientific and Industrial Research Organisation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000943","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI Ethics"],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The right to be forgotten (RTBF) allows individuals to request the removal of personal information from online platforms. Researchers have proposed machine unlearning algorithms as a solution for erasing specific data from trained models to support RTBF. However, these methods modify how data are fed into the model and how training is done, which may subsequently compromise AI ethics from the fairness perspective. To help AI practitioners make responsible decisions when adopting these unlearning methods, we present the first study on machine unlearning methods to reveal their fairness implications. We designed and conducted experiments on two typical machine unlearning methods (SISA and AmnesiacML) along with a retraining method (ORTR) as baseline using three fairness datasets under three different deletion strategies. Results show that non-uniform data deletion with the variant of SISA leads to better fairness compared to ORTR and AmnesiacML, while initial training and uniform data deletion do not necessarily affect the fairness of all three methods. This research can help practitioners make informed decisions when implementing RTBF solutions that consider potential trade-offs on fairness.<\/jats:p>","DOI":"10.1007\/s43681-023-00398-y","type":"journal-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T14:02:55Z","timestamp":1704290575000},"page":"83-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["To be forgotten or to be fair: unveiling fairness implications of machine unlearning methods"],"prefix":"10.1007","volume":"4","author":[{"given":"Dawen","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Shidong","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Thong","family":"Hoang","sequence":"additional","affiliation":[]},{"given":"Zhenchang","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Staples","sequence":"additional","affiliation":[]},{"given":"Xiwei","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Qinghua","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Liming","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,3]]},"reference":[{"key":"398_CR1","unstructured":"Adult Data Set (1996). https:\/\/archive.ics.uci.edu\/ml\/datasets\/adult"},{"key":"398_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal, A., Lohia, P., Nagar, S., Dey, K., Saha, D.: Black box fairness testing of machine learning models. In: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 625\u2013635 (2019)","DOI":"10.1145\/3338906.3338937"},{"key":"398_CR3","doi-asserted-by":"crossref","unstructured":"Ahmad, K., Bano, M., Abdelrazek, M., Arora, C., Grundy, J.: What\u2019s up with requirements engineering for artificial intelligence systems? In: 2021 IEEE 29th International Requirements Engineering Conference (RE), pp. 1\u201312. IEEE (2021)","DOI":"10.1109\/RE51729.2021.00008"},{"key":"398_CR4","unstructured":"Announcement: Privacy commissioner seeks federal court determination on key issue for Canadians\u2019 online reputation (2018). https:\/\/www.priv.gc.ca\/en\/opc-news\/news-and-announcements\/2018\/an_181010\/"},{"key":"398_CR5","unstructured":"Bank Marketing Data Set (2012). https:\/\/archive.ics.uci.edu\/ml\/datasets\/Bank+Marketing"},{"key":"398_CR6","doi-asserted-by":"publisher","first-page":"3203","DOI":"10.1007\/s10994-022-06178-9","volume":"111","author":"T Baumhauer","year":"2022","unstructured":"Baumhauer, T., Sch\u00f6ttle, P., Zeppelzauer, M.: Machine unlearning: linear filtration for logit-based classifiers. Mach. Learn. 111, 3203\u2013226 (2022)","journal-title":"Mach. Learn."},{"issue":"4\/5","key":"398_CR7","doi-asserted-by":"publisher","first-page":"4-1","DOI":"10.1147\/JRD.2019.2942287","volume":"63","author":"RK Bellamy","year":"2019","unstructured":"Bellamy, R.K., Dey, K., Hind, M., Hoffman, S.C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovi\u0107, A., et al.: AI Fairness 360: an extensible toolkit for detecting and mitigating algorithmic bias. IBM J. Res. Dev. 63(4\/5), 4\u20131 (2019)","journal-title":"IBM J. Res. Dev."},{"key":"398_CR8","doi-asserted-by":"crossref","unstructured":"Bertram, T., Bursztein, E., Caro, S., Chao, H., Feman, R.C., Fleischer, P., Gustafsson, A., Hemerly, J., Hibbert, C., Invernizzi, L., Donnelly, L.K., Ketover, J., Laefer, J., Nicholas, P., Niu, Y., Obhi, H., Price, D., Strait, A., Thomas, K., Verney, A.: Five years of the right to be forgotten. In Proceedings of the Conference on Computer and Communications Security (2019)","DOI":"10.1145\/3319535.3354208"},{"key":"398_CR9","doi-asserted-by":"crossref","unstructured":"Biswas, S., Rajan, H.: Do the machine learning models on a crowd sourced platform exhibit bias? an empirical study on model fairness. In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 642\u2013653 (2020)","DOI":"10.1145\/3368089.3409704"},{"key":"398_CR10","doi-asserted-by":"crossref","unstructured":"Bourtoule, L., Chandrasekaran, V., Choquette-Choo, C.A., Jia, H., Travers, A., Zhang, B., Lie, D., Papernot, N.: Machine unlearning. In: 2021 IEEE Symposium on Security and Privacy (SP), pp. 141\u2013159. IEEE (2021)","DOI":"10.1109\/SP40001.2021.00019"},{"issue":"2","key":"398_CR11","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s10618-010-0190-x","volume":"21","author":"T Calders","year":"2010","unstructured":"Calders, T., Verwer, S.: Three Naive Bayes approaches for discrimination-free classification. Data Min Knowl Discov 21(2), 277\u2013292 (2010)","journal-title":"Data Min Knowl Discov"},{"key":"398_CR12","unstructured":"California Consumer Privacy Act (2018). https:\/\/oag.ca.gov\/privacy\/ccpa"},{"key":"398_CR13","doi-asserted-by":"crossref","unstructured":"Cao, Y., Yang, J.: Towards making systems forget with machine unlearning. In: 2015 IEEE Symposium on Security and Privacy, pp. 463\u2013480. IEEE (2015)","DOI":"10.1109\/SP.2015.35"},{"key":"398_CR14","unstructured":"Cauwenberghs, G., Poggio, T.: Incremental and decremental support vector machine learning. In: Advances in Neural Information Processing Systems, vol. 13 (2000)"},{"key":"398_CR15","doi-asserted-by":"crossref","unstructured":"Chakraborty, J., Majumder, S., Yu, Z., Menzies, T.: Fairway: a way to build fair ml software. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 654\u2013665 (2020)","DOI":"10.1145\/3368089.3409697"},{"key":"398_CR16","unstructured":"Charter of Fundamental Rights and General Data Protection Regulation (2019). https:\/\/europa.eu\/eurobarometer\/surveys\/detail\/2222"},{"issue":"2","key":"398_CR17","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1089\/big.2016.0047","volume":"5","author":"A Chouldechova","year":"2017","unstructured":"Chouldechova, A.: Fair prediction with disparate impact: a study of bias in recidivism prediction instruments. Big Data 5(2), 153\u2013163 (2017)","journal-title":"Big Data"},{"key":"398_CR18","doi-asserted-by":"crossref","unstructured":"Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., Huq, A.: Algorithmic decision making and the cost of fairness. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 797\u2013806 (2017)","DOI":"10.1145\/3097983.3098095"},{"key":"398_CR19","unstructured":"Data and analysis for \u2019Machine Bias\u2019 (2017). https:\/\/github.com\/propublica\/compas-analysis"},{"key":"398_CR20","doi-asserted-by":"crossref","unstructured":"Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.: Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp. 214\u2013226 (2012)","DOI":"10.1145\/2090236.2090255"},{"key":"398_CR21","doi-asserted-by":"crossref","unstructured":"Finkelstein, A., Harman, M., Mansouri, S.A., Ren, J.; Zhang, Y.: \u201cFairness analysis\u201d in requirements assignments. In: 2008 16th IEEE International Requirements Engineering Conference, pp. 115\u2013124. IEEE (2008)","DOI":"10.1109\/RE.2008.61"},{"key":"398_CR22","unstructured":"General Data Protection Regulation (2016). https:\/\/gdpr-info.eu\/"},{"key":"398_CR23","doi-asserted-by":"crossref","unstructured":"Golatkar, A., Achille, A., Soatto, S.: Eternal sunshine of the spotless net: selective forgetting in deep networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9304\u20139312 (2020)","DOI":"10.1109\/CVPR42600.2020.00932"},{"key":"398_CR24","doi-asserted-by":"crossref","unstructured":"Graves, L., Nagisetty, V., Ganesh, V.: Amnesiac machine learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 13, pp. 11516\u201311524 (2021)","DOI":"10.1609\/aaai.v35i13.17371"},{"key":"398_CR25","unstructured":"Guo, C., Goldstein, T., Hannun, A., Van Der\u00a0Maaten, L.: Certified data removal from machine learning models. In: Daum\u00e9, H., III, Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pp. 3832\u20133842. PMLR (2020)"},{"key":"398_CR26","unstructured":"Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: Advances in Neural Information Processing systems, vol. 29 (2016a)"},{"key":"398_CR27","unstructured":"Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016b)"},{"key":"398_CR28","unstructured":"Izzo, Z., Smart, M. A., Chaudhuri, K., Zou, J.: Approximate data deletion from machine learning models (2020). arXiv:2002.10077"},{"issue":"7","key":"398_CR29","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1109\/TNN.2010.2048039","volume":"21","author":"M Karasuyama","year":"2010","unstructured":"Karasuyama, M., Takeuchi, I.: Multiple incremental decremental learning of support vector machines. IEEE Trans. Neural Netw. 21(7), 1048\u20131059 (2010)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"2","key":"398_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1970378.1970380","volume":"18","author":"W Li","year":"2011","unstructured":"Li, W., Matejka, J., Grossman, T., Konstan, J.A., Fitzmaurice, G.: Design and evaluation of a command recommendation system for software applications. ACM Trans. Comput. Hum. Interact.: TOCHI 18(2), 1\u201335 (2011)","journal-title":"ACM Trans. Comput. Hum. Interact.: TOCHI"},{"key":"398_CR31","doi-asserted-by":"crossref","unstructured":"Martinez, M., Stiefelhagen, R.: Taming the cross entropy loss. In: German Conference on Pattern Recognition, pp. 628\u2013637. Springer (2018)","DOI":"10.1007\/978-3-030-12939-2_43"},{"issue":"6","key":"398_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","volume":"54","author":"N Mehrabi","year":"2021","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv: CSUR 54(6), 1\u201335 (2021)","journal-title":"ACM Comput. Surv: CSUR"},{"key":"398_CR33","unstructured":"Menon, A.K., Williamson, R.C.: The cost of fairness in binary classification. In: Conference on Fairness, Accountability and Transparency, pp. 107\u2013118. PMLR (2018)"},{"key":"398_CR34","volume-title":"The First Civil Right: How Liberals Built Prison America","author":"N Murakawa","year":"2014","unstructured":"Murakawa, N.: The First Civil Right: How Liberals Built Prison America. Oxford University Press, Oxford (2014)"},{"key":"398_CR35","first-page":"26","volume":"4","author":"H Ramchoun","year":"2016","unstructured":"Ramchoun, H., Amine, M., Idrissi, J., Ghanou, Y., Ettaouil, M.: Multilayer Perceptron: Architecture Optimization and Training. In: International Journal of Interactive Multimedia & Artificial Intelligence, 4, 26\u201330 (2016)","journal-title":"International Journal of Interactive Multimedia & Artificial Intelligence"},{"key":"398_CR36","unstructured":"Ratner, A.J., Hancock, B., R\u00e9, C.: The role of massively multi-task and weak supervision in software 2.0. In: CIDR (2019)"},{"key":"398_CR37","doi-asserted-by":"crossref","unstructured":"Romero, E., Barrio, I., Belanche, L.: Incremental and decremental learning for linear support vector machines. In: de\u00a0S\u00e1, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds.) Artificial Neural Networks\u2014ICANN 2007, pp. 209\u2013218. Springer, Berlin. ISBN 978-3-540-74690-4 (2007)","DOI":"10.1007\/978-3-540-74690-4_22"},{"key":"398_CR38","first-page":"88","volume":"64","author":"J Rosen","year":"2011","unstructured":"Rosen, J.: The right to be forgotten. Stan. L. Rev. Online 64, 88 (2011)","journal-title":"Stan. L. Rev. Online"},{"issue":"5","key":"398_CR39","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1287\/inte.2018.0957","volume":"48","author":"C Rudin","year":"2018","unstructured":"Rudin, C., Ustun, B.: Optimized scoring systems: toward trust in machine learning for healthcare and criminal justice. Interfaces 48(5), 449\u2013466 (2018)","journal-title":"Interfaces"},{"key":"398_CR40","doi-asserted-by":"crossref","unstructured":"Singhal, P., Srivastava, P.K., Tiwari, A.K., Shukla, R.K.: A survey: approaches to facial detection and recognition with machine learning techniques. In: Proceedings of Second Doctoral Symposium on Computational Intelligence, pp. 103\u2013125. Springer (2022)","DOI":"10.1007\/978-981-16-3346-1_9"},{"issue":"12","key":"398_CR41","doi-asserted-by":"publisher","first-page":"3474","DOI":"10.14778\/3415478.3415570","volume":"13","author":"J Stoyanovich","year":"2020","unstructured":"Stoyanovich, J., Howe, B., Jagadish, H.V.: Responsible data management. Proc. VLDB Endow. 13(12), 3474\u20133488 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"398_CR42","doi-asserted-by":"crossref","unstructured":"Sun, Z., Zhang, J.M., Harman, M., Papadakis, M., Zhang, L.: Automatic testing and improvement of machine translation. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering, pp. 974\u2013985 (2020)","DOI":"10.1145\/3377811.3380420"},{"key":"398_CR43","unstructured":"Thompson, N.C., Greenewald, K., Lee, K., Manso, G.F.: The computational limits of deep learning (2020). arXiv:2007.05558"},{"key":"398_CR44","doi-asserted-by":"crossref","unstructured":"Tsai, C.-H., Lin, C.-Y., Lin, C.-J.: Incremental and decremental training for linear classification. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 343\u2013352 (2014)","DOI":"10.1145\/2623330.2623661"},{"key":"398_CR45","doi-asserted-by":"crossref","unstructured":"Udeshi, S., Arora, P., Chattopadhyay, S.: Automated directed fairness testing. In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering, pp. 98\u2013108 (2018)","DOI":"10.1145\/3238147.3238165"},{"issue":"1","key":"398_CR46","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1111\/0447-2778.00006","volume":"39","author":"N Upton","year":"2001","unstructured":"Upton, N., Teal, E.J., Felan, J.T.: Strategic and business planning practices of fast growth family firms. J. Small Bus. Manag. 39(1), 60\u201372 (2001)","journal-title":"J. Small Bus. Manag."},{"key":"398_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J.M., Harman, M.: Ignorance and prejudice\u201d in software fairness. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE), pp. 1436\u20131447. IEEE (2021)","DOI":"10.1109\/ICSE43902.2021.00129"},{"issue":"1","key":"398_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSE.2019.2962027","volume":"48","author":"JM Zhang","year":"2020","unstructured":"Zhang, J.M., Harman, M., Ma, L., Liu, Y.: Machine learning testing: survey, landscapes and horizons. IEEE Trans. Softw. Eng. 48(1), 1\u201336 (2020)","journal-title":"IEEE Trans. Softw. Eng."}],"container-title":["AI and Ethics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-023-00398-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-023-00398-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-023-00398-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T09:11:34Z","timestamp":1713172294000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43681-023-00398-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["398"],"URL":"https:\/\/doi.org\/10.1007\/s43681-023-00398-y","relation":{},"ISSN":["2730-5953","2730-5961"],"issn-type":[{"value":"2730-5953","type":"print"},{"value":"2730-5961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,3]]},"assertion":[{"value":"3 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}