{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:48:15Z","timestamp":1783738095713,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","funder":[{"name":"NSF CAREER Award","award":["2143706"],"award-info":[{"award-number":["2143706"]}]},{"name":"NSF Award","award":["2133169, 2232054"],"award-info":[{"award-number":["2133169, 2232054"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3715275.3732195","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:03:13Z","timestamp":1750698193000},"page":"3075-3093","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["The Data Minimization Principle in Machine Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8695-4128","authenticated-orcid":false,"given":"Prakhar","family":"Ganesh","sequence":"first","affiliation":[{"name":"Quebec Artificial Intelligence Institute (Mila), Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9958-7136","authenticated-orcid":false,"given":"Cuong","family":"Tran","sequence":"additional","affiliation":[{"name":"Dyania Health, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9816-0173","authenticated-orcid":false,"given":"Reza","family":"Shokri","sequence":"additional","affiliation":[{"name":"National University of Singapore (NUS), Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1381-6776","authenticated-orcid":false,"given":"Ferdinando","family":"Fioretto","sequence":"additional","affiliation":[{"name":"University of Virgnia, Charlottesville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. The EU Artificial Intelligence Act - Recital 69: Data Privacy. https:\/\/www.euaiact.com\/recital\/69."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_3_2_4_2","volume-title":"27th International Conference on Extending Database Technology, EDBT 2024","author":"Anciaux Nicolas","year":"2024","unstructured":"Nicolas Anciaux, Sabine Frittella, Baptiste Joffroy, Benjamin Nguyen, and Guillaume Scerri. 2024. A new PET for data collection via forms with data minimization, full accuracy and informed consent. In 27th International Conference on Extending Database Technology, EDBT 2024."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Asia\u00a0J. Biega and Mich\u00e8le Finck. 2021. Reviving Purpose Limitation and Data Minimisation in Data-Driven Systems. Technology and Regulation (Dec. 2021) 44\u201361 Pages.","DOI":"10.71265\/z7r0t122"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401034"},{"key":"e_1_3_3_2_7_2","volume-title":"Pattern recognition and machine learning","author":"Bishop Christopher\u00a0M","year":"2006","unstructured":"Christopher\u00a0M Bishop and Nasser\u00a0M Nasrabadi. 2006. Pattern recognition and machine learning. Vol.\u00a04. Springer."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Avrim\u00a0L Blum and Pat Langley. 1997. Selection of relevant features and examples in machine learning. Artificial intelligence 97 1-2 (1997) 245\u2013271.","DOI":"10.1016\/S0004-3702(97)00063-5"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Ziqian Chen Fei Sun Yifan Tang Haokun Chen Jinyang Gao and Bolin Ding. 2023. Studying the impact of data disclosure mechanism in recommender systems via simulation. ACM Transactions on Information Systems 41 3 (2023) 1\u201326.","DOI":"10.1145\/3569452"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Paulo Cortez Ant\u00f3nio Cerdeira Fernando Almeida Telmo Matos and Jos\u00e9 Reis. 2009. Modeling wine preferences by data mining from physicochemical properties. Decision support systems 47 4 (2009) 547\u2013553.","DOI":"10.1016\/j.dss.2009.05.016"},{"key":"e_1_3_3_2_11_2","unstructured":"Frances Ding Moritz Hardt John Miller and Ludwig Schmidt. 2021. Retiring adult: New datasets for fair machine learning. Advances in neural information processing systems 34 (2021) 6478\u20136490."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Simson Garfinkel John\u00a0M Abowd and Christian Martindale. 2019. Understanding database reconstruction attacks on public data. Commun. ACM 62 3 (2019) 46\u201353.","DOI":"10.1145\/3287287"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Abigail Goldsteen Gilad Ezov Ron Shmelkin Micha Moffie and Ariel Farkash. 2021. Data minimization for GDPR compliance in machine learning models. AI and Ethics (2021) 1\u201315.","DOI":"10.1007\/s43681-021-00095-8"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Jane Henriksen-Bulmer and Sheridan Jeary. 2016. Re-identification attacks\u2014A systematic literature review. International Journal of Information Management 36 6 (2016) 1184\u20131192.","DOI":"10.1016\/j.ijinfomgt.2016.08.002"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Peter\u00a0D. Hoff. 2007. Extending the Rank Likelihood for Semiparametric Copula Estimation. Annals of Applied Statistics 1 1 (2007) 265\u2013283.","DOI":"10.1214\/07-AOAS107"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCID.2011.151"},{"key":"e_1_3_3_2_18_2","volume-title":"ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH)","author":"James Hailey","year":"2023","unstructured":"Hailey James, Chirag Nagpal, Katherine\u00a0A Heller, and Berk Ustun. 2023. Participatory Personalization in Classification. In ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH)."},{"key":"e_1_3_3_2_19_2","unstructured":"Tobias Leemann Martin Pawelczyk Christian\u00a0Thomas Eberle and Gjergji Kasneci. 2022. I Prefer not to Say: Operationalizing Fair and User-guided Data Minimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.13954 (2022)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"S\u00e9rgio Moro Paulo Cortez and Paulo Rita. 2014. A data-driven approach to predict the success of bank telemarketing. Decision Support Systems 62 (2014) 22\u201331.","DOI":"10.1016\/j.dss.2014.03.001"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386790"},{"key":"e_1_3_3_2_23_2","unstructured":"Norwegian Data Protection Authority. 2018. Artificial Intelligence and Privacy. https:\/\/www.datatilsynet.no\/globalassets\/global\/english\/ai-and-privacy.pdf"},{"key":"e_1_3_3_2_24_2","unstructured":"Mansheej Paul Surya Ganguli and Gintare\u00a0Karolina Dziugaite. 2021. Deep learning on a data diet: Finding important examples early in training. Advances in Neural Information Processing Systems 34 (2021) 20596\u201320607."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-815032-0.00006-8"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Paul Quinn and Gianclaudio Malgieri. 2021. The difficulty of defining sensitive data\u2014The concept of sensitive data in the EU data protection framework. German Law Journal 22 8 (2021) 1583\u20131612.","DOI":"10.1017\/glj.2021.79"},{"key":"e_1_3_3_2_27_2","unstructured":"Bashir Rastegarpanah Krishna Gummadi and Mark Crovella. 2021. Auditing black-box prediction models for data minimization compliance. Advances in Neural Information Processing Systems 34 (2021) 20621\u201320632."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Maria Rigaki and Sebastian Garcia. 2023. A survey of privacy attacks in machine learning. Comput. Surveys 56 4 (2023) 1\u201334.","DOI":"10.1145\/3624010"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533148"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Ankur Sinha Pekka Malo Anton Frantsev and Kalyanmoy Deb. 2014. Finding optimal strategies in a multi-period multi-leader\u2013follower Stackelberg game using an evolutionary algorithm. Computers & Operations Research 41 (2014) 374\u2013385.","DOI":"10.1016\/j.cor.2013.07.010"},{"key":"e_1_3_3_2_32_2","unstructured":"Ben Sorscher Robert Geirhos Shashank Shekhar Surya Ganguli and Ari Morcos. 2022. Beyond neural scaling laws: beating power law scaling via data pruning. Advances in Neural Information Processing Systems 35 (2022) 19523\u201319536."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72927-3_24"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00089"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Louise Thomas Iqbal Gondal Taiwo Oseni and Selena\u00a0Sally Firmin. 2022. A framework for data privacy and security accountability in data breach communications. Computers & Security 116 (2022) 102657.","DOI":"10.1016\/j.cose.2022.102657"},{"key":"e_1_3_3_2_36_2","unstructured":"Ryan Tibshirani. 2015. Modeling Basics: Assessment Selection and Complexity. (2015). www.stat.cmu.edu\/\u00a0ryantibs\/statml"},{"key":"e_1_3_3_2_37_2","unstructured":"Cuong Tran and Ferdinando Fioretto. 2023. Personalized Privacy Auditing and Optimization at Test Time. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.00077 (2023)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2006-99412"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Lei Xu Adam Krzyzak and Ching\u00a0Y Suen. 1992. Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE transactions on systems man and cybernetics 22 3 (1992) 418\u2013435.","DOI":"10.1109\/21.155943"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"e_1_3_3_2_41_2","unstructured":"Sajjad Zarifzadeh Philippe Liu and Reza Shokri. 2023. Low-Cost High-Power Membership Inference Attacks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.03262 (2023)."}],"event":{"name":"FAccT '25: The 2025 ACM Conference on Fairness, Accountability, and Transparency","location":"Athens Greece","acronym":"FAccT '25"},"container-title":["Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715275.3732195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:27:20Z","timestamp":1750764440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715275.3732195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":40,"alternative-id":["10.1145\/3715275.3732195","10.1145\/3715275"],"URL":"https:\/\/doi.org\/10.1145\/3715275.3732195","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}