{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T07:24:04Z","timestamp":1792653844981,"version":"4.5.0"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:p>Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos. Our proposed algorithm directly ensures user-level DP through per-user weighted clipping, departing from group-privacy approaches. We provide a theoretical analysis of the algorithm's privacy and utility. Additionally, we improve the utility of the proposed algorithm with an enhanced weighting strategy based on user record distribution and design a novel private protocol that ensures no additional information is revealed to the silos and the server. Experiments on real-world datasets show substantial improvements in our methods in privacy-utility trade-offs under user-level DP compared to baseline methods. To the best of our knowledge, our work is the first FL framework that effectively provides user-level DP in the general cross-silo FL setting.<\/jats:p>","DOI":"10.14778\/3681954.3681966","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T16:23:36Z","timestamp":1725035016000},"page":"2826-2839","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy"],"prefix":"10.14778","volume":"17","author":[{"given":"Fumiyuki","family":"Kato","sequence":"first","affiliation":[{"name":"Kyoto University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Xiong","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Takagi","sequence":"additional","affiliation":[{"name":"Kyoto University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masatoshi","family":"Yoshikawa","sequence":"additional","affiliation":[{"name":"Osaka Seikei University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,30]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_2_1_2_1","first-page":"5052","article-title":"The skellam mechanism for differentially private federated learning","volume":"34","author":"Agarwal Naman","year":"2021","unstructured":"Naman Agarwal, Peter Kairouz, and Ziyu Liu. 2021. The skellam mechanism for differentially private federated learning. Advances in Neural Information Processing Systems 34 (2021), 5052--5064.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3094788"},{"key":"e_1_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 263--271","author":"Amin Kareem","year":"2019","unstructured":"Kareem Amin, Alex Kulesza, Andres Munoz, and Sergei Vassilvtiskii. 2019. Bounding user contributions: A bias-variance trade-off in differential privacy. In International Conference on Machine Learning. PMLR, 263--271."},{"key":"e_1_2_1_5_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 2496--2506","author":"Balle Borja","year":"2020","unstructured":"Borja Balle, Gilles Barthe, Marco Gaboardi, Justin Hsu, and Tetsuya Sato. 2020. Hypothesis testing interpretations and renyi differential privacy. In International Conference on Artificial Intelligence and Statistics. PMLR, 2496--2506."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417885"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17653-2_13"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73458-1_30"},{"key":"e_1_2_1_10_1","unstructured":"data61. [n.d.]. https:\/\/github.com\/data61\/python-paillier."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"e_1_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Cynthia Dwork Aaron Roth et al. 2014. The algorithmic foundations of differential privacy. Foundations and Trends\u00ae in Theoretical Computer Science 9 3--4 (2014) 211--407.","DOI":"10.1561\/0400000042"},{"key":"e_1_2_1_14_1","first-page":"13999","article-title":"Smoothly bounding user contributions in differential privacy","volume":"33","author":"Epasto Alessandro","year":"2020","unstructured":"Alessandro Epasto, Mohammad Mahdian, Jieming Mao, Vahab Mirrokni, and Lijie Ren. 2020. Smoothly bounding user contributions in differential privacy. Advances in Neural Information Processing Systems 33 (2020), 13999--14010.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_15_1","volume-title":"shuffle, analyze privacy revisited: Formalizations and empirical evaluation. arXiv preprint arXiv:2001.03618","author":"Erlingsson \u00dalfar","year":"2020","unstructured":"\u00dalfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Shuang Song, Kunal Talwar, and Abhradeep Thakurta. 2020. Encode, shuffle, analyze privacy revisited: Formalizations and empirical evaluation. arXiv preprint arXiv:2001.03618 (2020)."},{"key":"e_1_2_1_16_1","volume-title":"NIPS 2017 Workshop: Machine Learning on the Phone and other Consumer Devices","author":"Geyer Robin C","year":"2017","unstructured":"Robin C Geyer, Tassilo Klein, and Moin Nabi. 2017. Differentially private federated learning: A client level perspective. NIPS 2017 Workshop: Machine Learning on the Phone and other Consumer Devices (2017)."},{"key":"e_1_2_1_17_1","first-page":"19586","article-title":"An efficient framework for clustered federated learning","volume":"33","author":"Ghosh Avishek","year":"2020","unstructured":"Avishek Ghosh, Jichan Chung, Dong Yin, and Kannan Ramchandran. 2020. An efficient framework for clustered federated learning. Advances in Neural Information Processing Systems 33 (2020), 19586--19597.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_18_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 2521--2529","author":"Girgis Antonious","year":"2021","unstructured":"Antonious Girgis, Deepesh Data, Suhas Diggavi, Peter Kairouz, and Ananda Theertha Suresh. 2021. Shuffled model of differential privacy in federated learning. In International Conference on Artificial Intelligence and Statistics. PMLR, 2521--2529."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.2501\/IJMR-2017-050"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3361338.3361469"},{"key":"e_1_2_1_21_1","unstructured":"Kaggle. 2018. Credit Card Fraud Detection dataset. https:\/\/www.kaggle.com\/datasets\/mlg-ulb\/creditcardfraud. Accessed: 2023-08-03."},{"key":"e_1_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 5201--5212","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, Ziyu Liu, and Thomas Steinke. 2021. The distributed discrete gaussian mechanism for federated learning with secure aggregation. In International Conference on Machine Learning. PMLR, 5201--5212."},{"key":"e_1_2_1_23_1","volume-title":"Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al.","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, H Brendan McMahan, Brendan Avent, Aur\u00e9lien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. 2021. Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning 14, 1--2 (2021), 1--210."},{"key":"e_1_2_1_24_1","volume-title":"Algorithms for Private Data Analysis","author":"Kamath Gautam","year":"2020","unstructured":"Gautam Kamath. 2020. CS 860 : Algorithms for Private Data Analysis Fall 2020 Lecture 5 --- Approximate Differential Privacy. http:\/\/www.gautamkamath.com\/CS860notes\/lec5.pdf. [Online; accessed 23-June-2023]."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-81242-3_3"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/3603581.3603583"},{"key":"e_1_2_1_27_1","volume-title":"ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy. arXiv preprint arXiv:2308.12210","author":"Kato Fumiyuki","year":"2023","unstructured":"Fumiyuki Kato, Li Xiong, Shun Takagi, Yang Cao, and Masatoshi Yoshikawa. 2023. ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy. arXiv preprint arXiv:2308.12210 (2023)."},{"key":"e_1_2_1_28_1","first-page":"12466","article-title":"Learning with user-level privacy","volume":"34","author":"Levy Daniel","year":"2021","unstructured":"Daniel Levy, Ziteng Sun, Kareem Amin, Satyen Kale, Alex Kulesza, Mehryar Mohri, and Ananda Theertha Suresh. 2021. Learning with user-level privacy. Advances in Neural Information Processing Systems 34 (2021), 12466--12479.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526162"},{"key":"e_1_2_1_30_1","first-page":"5925","article-title":"On privacy and personalization in cross-silo federated learning","volume":"35","author":"Liu Ken","year":"2022","unstructured":"Ken Liu, Shengyuan Hu, Steven Z Wu, and Virginia Smith. 2022. On privacy and personalization in cross-silo federated learning. Advances in Neural Information Processing Systems 35 (2022), 5925--5940.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_31_1","first-page":"20965","article-title":"Learning discrete distributions: user vs item-level privacy","volume":"33","author":"Liu Yuhan","year":"2020","unstructured":"Yuhan Liu, Ananda Theertha Suresh, Felix Xinnan X Yu, Sanjiv Kumar, and Michael Riley. 2020. Learning discrete distributions: user vs item-level privacy. Advances in Neural Information Processing Systems 33 (2020), 20965--20976.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_32_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 5749--5786","author":"Lowy Andrew","year":"2023","unstructured":"Andrew Lowy, Ali Ghafelebashi, and Meisam Razaviyayn. 2023. Private non-convex federated learning without a trusted server. In International Conference on Artificial Intelligence and Statistics. PMLR, 5749--5786."},{"key":"e_1_2_1_33_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TVY6GoURrw","author":"Lowy Andrew","year":"2023","unstructured":"Andrew Lowy and Meisam Razaviyayn. 2023. Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TVY6GoURrw"},{"key":"e_1_2_1_34_1","volume-title":"A general approach to adding differential privacy to iterative training procedures. arXiv preprint arXiv:1812.06210","author":"McMahan H Brendan","year":"2018","unstructured":"H Brendan McMahan, Galen Andrew, Ulfar Erlingsson, Steve Chien, Ilya Mironov, Nicolas Papernot, and Peter Kairouz. 2018. A general approach to adding differential privacy to iterative training procedures. arXiv preprint arXiv:1812.06210 (2018)."},{"key":"e_1_2_1_35_1","volume-title":"Federated learning of deep networks using model averaging. arXiv preprint arXiv:1602.05629","author":"McMahan H Brendan","year":"2016","unstructured":"H Brendan McMahan, Eider Moore, Daniel Ramage, and Blaise Ag\u00fcera y Arcas. 2016. Federated learning of deep networks using model averaging. arXiv preprint arXiv:1602.05629 (2016)."},{"key":"e_1_2_1_36_1","volume-title":"Learning differentially private recurrent language models. arXiv preprint arXiv:1710.06963","author":"McMahan H Brendan","year":"2017","unstructured":"H Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang. 2017. Learning differentially private recurrent language models. arXiv preprint arXiv:1710.06963 (2017)."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559850"},{"key":"e_1_2_1_38_1","volume-title":"R\u00e9nyi differential privacy. In 2017 IEEE 30th computer security foundations symposium (CSF)","author":"Mironov Ilya","unstructured":"Ilya Mironov. 2017. R\u00e9nyi differential privacy. In 2017 IEEE 30th computer security foundations symposium (CSF). IEEE, 263--275."},{"key":"e_1_2_1_39_1","volume-title":"arXiv preprint arXiv:1908.10530","author":"Mironov Ilya","year":"2019","unstructured":"Ilya Mironov, Kunal Talwar, and Li Zhang. 2019. R\\'enyi differential privacy of the sampled gaussian mechanism. arXiv preprint arXiv:1908.10530 (2019)."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3466628"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"e_1_2_1_42_1","volume-title":"Marco Lorenzi, Giovanni Neglia, Marc Tommasi, and Mathieu Andreux.","author":"du Terrail Jean Ogier","year":"2022","unstructured":"Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Tele\u0144czuk, Shadi Albarqouni, Salman Avestimehr, Aur\u00e9lien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, and Mathieu Andreux. 2022. FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 5315--5334."},{"key":"e_1_2_1_43_1","volume-title":"Luke Carlson, Filip Granqvist, Chris Vandevelde, et al.","author":"Paulik Matthias","year":"2021","unstructured":"Matthias Paulik, Matt Seigel, Henry Mason, Dominic Telaar, Joris Kluivers, Rogier van Dalen, Chi Wai Lau, Luke Carlson, Filip Granqvist, Chris Vandevelde, et al. 2021. Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications. arXiv preprint arXiv:2102.08503 (2021)."},{"key":"e_1_2_1_44_1","volume-title":"Federated learning for emoji prediction in a mobile keyboard. arXiv preprint arXiv:1906.04329","author":"Ramaswamy Swaroop","year":"2019","unstructured":"Swaroop Ramaswamy, Rajiv Mathews, Kanishka Rao, and Fran\u00e7oise Beaufays. 2019. Federated learning for emoji prediction in a mobile keyboard. arXiv preprint arXiv:1906.04329 (2019)."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26177"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSF57540.2023.00034"},{"key":"e_1_2_1_47_1","volume-title":"Privacy-preserving record linkage for big data: Current approaches and research challenges. Handbook of big data technologies","author":"Vatsalan Dinusha","year":"2017","unstructured":"Dinusha Vatsalan, Ziad Sehili, Peter Christen, and Erhard Rahm. 2017. Privacy-preserving record linkage for big data: Current approaches and research challenges. Handbook of big data technologies (2017), 851--895."},{"key":"e_1_2_1_48_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 1226--1235","author":"Wang Yu-Xiang","year":"2019","unstructured":"Yu-Xiang Wang, Borja Balle, and Shiva Prasad Kasiviswanathan. 2019. Subsampled r\u00e9nyi differential privacy and analytical moments accountant. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 1226--1235."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2020-0025"},{"key":"e_1_2_1_50_1","volume-title":"Proceedings of ICLR","author":"Yang Haibo","year":"2021","unstructured":"Haibo Yang, Minghong Fang, and Jia Liu. 2021. Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning. Proceedings of ICLR (2021)."},{"key":"e_1_2_1_51_1","volume-title":"FPGA-based hardware accelerator of homomorphic encryption for efficient federated learning. arXiv preprint arXiv:2007.10560","author":"Yang Zhaoxiong","year":"2020","unstructured":"Zhaoxiong Yang, Shuihai Hu, and Kai Chen. 2020. FPGA-based hardware accelerator of homomorphic encryption for efficient federated learning. arXiv preprint arXiv:2007.10560 (2020)."},{"key":"e_1_2_1_52_1","volume-title":"Opacus: User-friendly differential privacy library in PyTorch. arXiv preprint arXiv:2109.12298","author":"Yousefpour Ashkan","year":"2021","unstructured":"Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, et al. 2021. Opacus: User-friendly differential privacy library in PyTorch. arXiv preprint arXiv:2109.12298 (2021)."},{"key":"e_1_2_1_53_1","volume-title":"Konda Reddy Mopuri, and Hakan Bilen","author":"Zhao Bo","year":"2020","unstructured":"Bo Zhao, Konda Reddy Mopuri, and Hakan Bilen. 2020. idlg: Improved deep leakage from gradients. arXiv preprint arXiv:2001.02610 (2020)."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3681954.3681966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:29:13Z","timestamp":1725474553000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3681954.3681966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":53,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.14778\/3681954.3681966"],"URL":"https:\/\/doi.org\/10.14778\/3681954.3681966","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"2024-08-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}