{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:03:22Z","timestamp":1776276202463,"version":"3.50.1"},"reference-count":24,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T00:00:00Z","timestamp":1741737600000},"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":["ACM Trans. Model. Perform. Eval. Comput. Syst."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>We propose, analyze, and experimentally evaluate a novel secure aggregation algorithm targeted at cross-organizational federated learning applications with a fixed set of participating learners. Our solution organizes learners in a chain and encrypts all traffic to reduce the controller of the aggregation to a mere message broker. We show that our algorithm scales better and is less resource demanding than existing solutions, while being easy to implement on constrained platforms.<\/jats:p>\n          <jats:p>With 36 nodes, our method outperforms state-of-the-art secure aggregation by 70x, and 56x with and without failover, respectively.<\/jats:p>","DOI":"10.1145\/3716630","type":"journal-article","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T11:04:17Z","timestamp":1738926257000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SAFE: Secure Aggregation with Failover and Encryption"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0554-3584","authenticated-orcid":false,"given":"Thomas","family":"Sandholm","sequence":"first","affiliation":[{"name":"NextGen Systems, CableLabs, Santa Clara, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0472-2145","authenticated-orcid":false,"given":"Sayandev","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"NextGen Systems, CableLabs, Santa Clara, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6783-0864","authenticated-orcid":false,"given":"Bernardo","family":"Huberman","sequence":"additional","affiliation":[{"name":"NextGen Systems, CableLabs, Santa Clara, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,12]]},"reference":[{"key":"e_1_3_3_2_2","article-title":"Advances and open problems in federated learning","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. arXiv preprint arXiv:1912.04977 (2021).","journal-title":"arXiv preprint arXiv:1912.04977"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"e_1_3_3_4_2","volume-title":"NIPS Workshop on Private Multi-Party Machine Learning","author":"Bonawitz Keith A.","year":"2016","unstructured":"Keith A. Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2016. Practical secure aggregation for federated learning on user-held data. In NIPS Workshop on Private Multi-Party Machine Learning. https:\/\/arxiv.org\/abs\/1611.04482"},{"key":"e_1_3_3_5_2","first-page":"1","article-title":"Privacy and data balkanization: Circumventing the barriers","author":"Huberman Bernardo A.","year":"2021","unstructured":"Bernardo A. Huberman and Tad Hogg. 2021. Privacy and data balkanization: Circumventing the barriers. AI and Ethics (2021), 1\u20137.","journal-title":"AI and Ethics"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"e_1_3_3_7_2","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu Ligeng","year":"2019","unstructured":"Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep leakage from gradients. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3054610"},{"key":"e_1_3_3_10_2","article-title":"Communication-computation efficient secure aggregation for federated learning","author":"Choi Beongjun","year":"2020","unstructured":"Beongjun Choi, Jy-yong Sohn, Dong-Jun Han, and Jaekyun Moon. 2020. Communication-computation efficient secure aggregation for federated learning. arXiv preprint arXiv:2012.05433 (2020).","journal-title":"arXiv preprint arXiv:2012.05433"},{"key":"e_1_3_3_11_2","article-title":"Efficient sparse secure aggregation for federated learning","author":"Beguier Constance","year":"2020","unstructured":"Constance Beguier, Mathieu Andreux, and Eric W. Tramel. 2020. Efficient sparse secure aggregation for federated learning. arXiv preprint arXiv:2007.14861 (2020).","journal-title":"arXiv preprint arXiv:2007.14861"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/SPW53761.2021.00017"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179468"},{"key":"e_1_3_3_14_2","article-title":"Can you really backdoor federated learning?","author":"Sun Ziteng","year":"2019","unstructured":"Ziteng Sun, Peter Kairouz, Ananda Theertha Suresh, and H. Brendan McMahan. 2019. Can you really backdoor federated learning? arXiv preprint arXiv:1911.07963 (2019).","journal-title":"arXiv preprint arXiv:1911.07963"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179434"},{"key":"e_1_3_3_16_2","article-title":"FastSecAgg: Scalable secure aggregation for privacy-preserving federated learning","author":"Kadhe Swanand","year":"2020","unstructured":"Swanand Kadhe, Nived Rajaraman, O. Ozan Koyluoglu, and Kannan Ramchandran. 2020. FastSecAgg: Scalable secure aggregation for privacy-preserving federated learning. arXiv preprint arXiv:2009.11248 (2020).","journal-title":"arXiv preprint arXiv:2009.11248"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242702"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01585-4"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0009"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417885"},{"key":"e_1_3_3_21_2","first-page":"493","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC\u201920)","author":"Zhang Chengliang","year":"2020","unstructured":"Chengliang Zhang, Suyi Li, Junzhe Xia, Wei Wang, Feng Yan, and Yang Liu. 2020. BatchCrypt: Efficient homomorphic encryption for Cross-Silo federated learning. In 2020 USENIX Annual Technical Conference (USENIX ATC\u201920). 493\u2013506."},{"issue":"2","key":"e_1_3_3_22_2","article-title":"A pragmatic introduction to secure multi-party computation","volume":"2","author":"Evans David","year":"2017","unstructured":"David Evans, Vladimir Kolesnikov, and Mike Rosulek. 2017. A pragmatic introduction to secure multi-party computation. Foundations and Trends\u00ae in Privacy and Security 2, 2-3 (2017).","journal-title":"Foundations and Trends\u00ae in Privacy and Security"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/65.806987"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3563701"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10796-020-10086-5"}],"container-title":["ACM Transactions on Modeling and Performance Evaluation of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716630","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:52Z","timestamp":1750295932000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,12]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3716630"],"URL":"https:\/\/doi.org\/10.1145\/3716630","relation":{},"ISSN":["2376-3639","2376-3647"],"issn-type":[{"value":"2376-3639","type":"print"},{"value":"2376-3647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,12]]},"assertion":[{"value":"2024-04-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}