{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T20:34:08Z","timestamp":1770582848543,"version":"3.49.0"},"reference-count":19,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Queue"],"published-print":{"date-parts":[[2021,10,31]]},"abstract":"<jats:p>Centralized data collection can expose individuals to privacy risks and organizations to legal risks if data is not properly managed. Federated learning is a machine learning setting where multiple entities collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client's raw data is stored locally and not exchanged or transferred; instead, focused updates intended for immediate aggregation are used to achieve the learning objective. This article provides a brief introduction to key concepts in federated learning and analytics with an emphasis on how privacy technologies may be combined in real-world systems and how their use charts a path toward societal benefit from aggregate statistics in new domains and with minimized risk to individuals and to the organizations who are custodians of the data.<\/jats:p>","DOI":"10.1145\/3494834.3500240","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T23:04:23Z","timestamp":1637103863000},"page":"87-114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":60,"title":["Federated Learning and Privacy"],"prefix":"10.1145","volume":"19","author":[{"given":"Kallista","family":"Bonawitz","sequence":"first","affiliation":[{"name":"Google"}]},{"given":"Peter","family":"Kairouz","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Brendan","family":"McMahan","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Daniel","family":"Ramage","sequence":"additional","affiliation":[{"name":"Google"}]}],"member":"320","published-online":{"date-parts":[[2021,11,16]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_2_1_2_1","volume-title":"Privacy amplification via random check-ins. arXiv","author":"Balle B.","year":"2007","unstructured":"Balle, B., Kairouz, P., McMahan, H. B., Thakkar, O., Thakurta, A. 2020. Privacy amplification via random check-ins. arXiv; https:\/\/arxiv.org\/pdf\/2007.06605.pdf."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417885"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132769"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the 2nd SysML Conference","author":"Bonawitz K.","year":"2019","unstructured":"Bonawitz, K., et al. 2019. Towards federated learning at scale: system design. Proceedings of the 2nd SysML Conference, Palo Alto, CA, USA, 2019. https:\/\/arxiv.org\/pdf\/1902.01046.pdf."},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of the 28th Usenix Security Symposium, 267-284; https:\/\/dl.acm.org\/doi\/10","author":"Carlini N.","year":"2019","unstructured":"Carlini, N., Liu, C., Erlingsson, U., Kos, J., Song, D. 2019. The secret sharer: evaluating and testing unintended memorization neural networks. In Proceedings of the 28th Usenix Security Symposium, 267-284; https:\/\/dl.acm.org\/doi\/10.5555\/3361338.3361358."},{"key":"e_1_2_1_8_1","volume-title":"Extracting training data from large language models. arXiv preprint","author":"Carlini N.","year":"2012","unstructured":"Carlini, N., et al. 2020. Extracting training data from large language models. arXiv preprint; https:\/\/arxiv.org\/abs\/2012.07805."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"e_1_2_1_10_1","volume-title":"Advances and open problems in federated learning. Foundations and Trends in Machine Learning: 14 (1-2)","author":"Kairouz P.","year":"1912","unstructured":"Kairouz, P., et al. 2021. Advances and open problems in federated learning. Foundations and Trends in Machine Learning: 14 (1-2); https:\/\/arxiv.org\/abs\/1912.04977."},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (PMLR). 139","author":"Kairouz P.","year":"2021","unstructured":"Kairouz, P., Liu, Z., Steinke, T. 2021. The distributed discrete Gaussian mechanism for federated learning with secure aggregation. In Proceedings of the 38th International Conference on Machine Learning (PMLR). 139, 5201-5212; http:\/\/proceedings.mlr.press\/v139\/kairouz21a\/kairouz21a.pdf."},{"issue":"3","key":"e_1_2_1_12_1","article-title":"What can we learn privately","volume":"40","author":"Kasiviswanathan S. P.","year":"2011","unstructured":"Kasiviswanathan, S. P., Lee, H. K., Nissim, K., Raskhodnikova, S., Smith, A. 2011. What can we learn privately? SIAM (Society for Industrial and Applied Mathematics) Journal on Computing 40(3), 793?826; https:\/\/dl.acm.org\/doi\/10.1137\/090756090.","journal-title":"SIAM (Society for Industrial and Applied Mathematics) Journal on Computing"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 1273?1282; http:\/\/proceedings.mlr.press\/v54\/mcmahan17a\/mcmahan17a.pdf.","author":"McMahan H. B.","year":"2017","unstructured":"McMahan, H. B., Moore, E., Ramage, D., Hampson, S., Ag\u00fcera y Arcas, B. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 1273?1282; http:\/\/proceedings.mlr.press\/v54\/mcmahan17a\/mcmahan17a.pdf."},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR); https:\/\/openreview.net\/pdf?id=BJ0hF1Z0b.","author":"McMahan H. B.","year":"2018","unstructured":"McMahan, H. B., Ramage, D., Talwar, K., Zhang, L. 2018. Learning differentially private recurrent language models. In Proceedings of the International Conference on Learning Representations (ICLR); https:\/\/openreview.net\/pdf?id=BJ0hF1Z0b."},{"key":"e_1_2_1_15_1","series-title":"April 6","volume-title":"Federated Learning: Collaborative Machine Learning without Centralized Training Data. Google AI Blog","author":"McMahan H.B.","year":"2017","unstructured":"McMahan, H.B., Ramage, D. 2017. Federated Learning: Collaborative Machine Learning without Centralized Training Data. Google AI Blog (April 6); https:\/\/ai.googleblog.com\/2017\/04\/federated-learning-collaborative.html"},{"key":"e_1_2_1_16_1","unstructured":"Paulik M. et al. 2021. Federated evaluation and tuning for on-device personalization: system design & applications. arXiv preprint; https:\/\/arxiv.org\/abs\/2102.08503."},{"key":"e_1_2_1_17_1","series-title":"May 27","volume-title":"Federated analytics: collaborative data science without data collection. Google AI Blog","author":"Ramage D.","year":"2020","unstructured":"Ramage, D., Mazzocchi, S. 2020. Federated analytics: collaborative data science without data collection. Google AI Blog (May 27); https:\/\/ai.googleblog.com\/2020\/05\/federated-analytics-collaborative-data.html."},{"key":"e_1_2_1_18_1","volume-title":"Training production language models without memorizing user data. arXiv preprint","author":"Ramaswamy S.","year":"2009","unstructured":"Ramaswamy, S., et al. 2020. Training production language models without memorizing user data. arXiv preprint; https:\/\/arxiv.org\/abs\/2009.10031."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134098"}],"container-title":["Queue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3494834.3500240","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3494834.3500240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:18Z","timestamp":1750188678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3494834.3500240"}},"subtitle":["Building privacy-preserving systems for machine learning and data science on decentralized data"],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":19,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,10,31]]}},"alternative-id":["10.1145\/3494834.3500240"],"URL":"https:\/\/doi.org\/10.1145\/3494834.3500240","relation":{},"ISSN":["1542-7730","1542-7749"],"issn-type":[{"value":"1542-7730","type":"print"},{"value":"1542-7749","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,31]]},"assertion":[{"value":"2021-11-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}