{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:00:55Z","timestamp":1740171655291,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:00:00Z","timestamp":1692921600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:00:00Z","timestamp":1692921600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"abstract":"Abstract<\/jats:title>Federated learning is a semi-distributed algorithm, where a server communicates with multiple dispersed clients to learn a global model. The federated architecture is not robust and is sensitive to communication and computational overloads due to its one-master multi-client structure. It can also be subject to privacy attacks targeting personal information on the communication links. In this work, we introduce graph federated learning, which consists of multiple federated units connected by a graph. We then show how graph-homomorphic perturbations can be used to ensure the algorithm is differentially private on the server level. While on the client level, we show that improvement in the differentially private federated learning algorithm can be attained through the addition of random noise to the updates, as opposed to the models. We conduct both convergence and privacy theoretical analyses and illustrate performance by means of computer simulations.<\/jats:p>","DOI":"10.1186\/s13634-023-01049-4","type":"journal-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T15:02:14Z","timestamp":1692975734000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Privatized graph federated learning"],"prefix":"10.1186","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6902-2329","authenticated-orcid":false,"given":"Elsa","family":"Rizk","sequence":"first","affiliation":[]},{"given":"Stefan","family":"Vlaski","sequence":"additional","affiliation":[]},{"given":"Ali H.","family":"Sayed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,25]]},"reference":[{"key":"1049_CR1","unstructured":"H.B. McMahan, E. Moore, D. Ramage, S. Hampson, Communication-efficient learning of deep networks from decentralized data, in Proceedings of the International Conference on Artificial Intelligence and Statistics, vol. 54 (2017), pp. 1273\u20131282"},{"key":"1049_CR2","doi-asserted-by":"crossref","unstructured":"B. Hitaj, G. Ateniese, F. Perez-Cruz, Deep models under the GAN: information leakage from collaborative deep learning, in Proceedings of ACM SIGSAC Conference on Computer and Communications Security, New York, NY, USA (2017), pp. 603\u2013618","DOI":"10.1145\/3133956.3134012"},{"key":"1049_CR3","doi-asserted-by":"crossref","unstructured":"L. Melis, C. Song, E. De Cristofaro, V. Shmatikov, Exploiting unintended feature leakage in collaborative learning, in IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA (2019), pp. 691\u2013706","DOI":"10.1109\/SP.2019.00029"},{"key":"1049_CR4","doi-asserted-by":"crossref","unstructured":"M. Nasr, R. Shokri, A. Houmansadr, Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning, in IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA (2019), pp. 739\u2013753","DOI":"10.1109\/SP.2019.00065"},{"key":"1049_CR5","doi-asserted-by":"crossref","unstructured":"L. Zhu, S. Han, Deep leakage from gradients, in Advances in Neural Information Processing Systems, Vancouver, Canada (2019), pp. 17\u201331","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"1049_CR6","doi-asserted-by":"crossref","unstructured":"S.Vlaski, A.H. Sayed, Graph-homomorphic perturbations for private decentralized learning, in Proceedings of the ICASSP, Toronto, Canada (2021), pp. 1\u20135","DOI":"10.1109\/ICASSP39728.2021.9413811"},{"key":"1049_CR7","doi-asserted-by":"crossref","unstructured":"L. Liu, J. Zhang, S.H. Song, K.B. Letaief, Client-edge-cloud hierarchical federated learning, in IEEE International Conference on Communications (ICC) (2020), pp. 1\u20136","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"1049_CR8","doi-asserted-by":"crossref","unstructured":"E. Rizk, A.H. Sayed, A graph federated architecture with privacy preserving learning, in IEEE International Workshop on Signal Processing Advances in Wireless Communications, Lucca, Italy (2021), pp. 1\u20135. arxiv:2104.13215","DOI":"10.1109\/SPAWC51858.2021.9593148"},{"key":"1049_CR9","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TSIPN.2022.3151242","volume":"8","author":"W Liu","year":"2022","unstructured":"W. Liu, L. Chen, W. Zhang, Decentralized federated learning: balancing communication and computing costs. IEEE Trans. Signal Inf. Process. Over Netw. 8, 131\u2013143 (2022)","journal-title":"IEEE Trans. Signal Inf. Process. Over Netw."},{"key":"1049_CR10","doi-asserted-by":"crossref","unstructured":"B. Wang, J. Fang, H. Li, X. Yuan, Q. Ling, Confederated learning: federated learning with decentralized edge servers. arXiv:2205.14905 (2022)","DOI":"10.1109\/TSP.2023.3241768"},{"key":"1049_CR11","unstructured":"R.C. Geyer, T. Klein, M. Nabi, Differentially private federated learning: a client level perspective. arXiv:1712.07557 (2017)"},{"issue":"10","key":"1049_CR12","doi-asserted-by":"publisher","first-page":"9530","DOI":"10.1109\/JIOT.2020.2991416","volume":"7","author":"R Hu","year":"2020","unstructured":"R. Hu, Y. Guo, H. Li, Q. Pei, Y. Gong, Personalized federated learning with differential privacy. IEEE Internet Things J. 7(10), 9530\u20139539 (2020)","journal-title":"IEEE Internet Things J."},{"key":"1049_CR13","doi-asserted-by":"crossref","unstructured":"A. Triastcyn, B. Faltings, Federated learning with Bayesian differential privacy, in IEEE International Conference on Big Data, Los Angeles, California, USA (2019), pp. 2587\u20132596","DOI":"10.1109\/BigData47090.2019.9005465"},{"key":"1049_CR14","doi-asserted-by":"crossref","unstructured":"S. Truex, L. Liu, K.-H. Chow, M.E. Gursoy, W. Wei, LDP-FED: federated learning with local differential privacy, in Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking (2020), pp. 61\u201366","DOI":"10.1145\/3378679.3394533"},{"key":"1049_CR15","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","volume":"15","author":"K Wei","year":"2020","unstructured":"K. Wei, J. Li, M. Ding, C. Ma, H.H. Yang, F. Farokhi, S. Jin, T.Q. Quek, H.V. Poor, Federated learning with differential privacy: algorithms and performance analysis. IEEE Trans. Inf. Forensics Secur. 15, 3454\u20133469 (2020)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"1049_CR16","unstructured":"B. Jayaraman, L. Wang, D. Evans, Q. Gu, Distributed learning without distress: privacy-preserving empirical risk minimization, in Advances in Neural Information Processing Systems, vol. 31. Montreal, Canada (2018)"},{"issue":"8","key":"1049_CR17","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1109\/TKDE.2018.2794384","volume":"30","author":"C Li","year":"2018","unstructured":"C. Li, P. Zhou, L. Xiong, Q. Wang, T. Wang, Differentially private distributed online learning. IEEE Trans. Knowl. Data Eng. 30(8), 1440\u20131453 (2018)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"1049_CR18","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TSIPN.2018.2797806","volume":"4","author":"J Zhu","year":"2018","unstructured":"J. Zhu, C. Xu, J. Guan, D.O. Wu, Differentially private distributed online algorithms over time-varying directed networks. IEEE Trans. Signal Inf. Process. Over Netw. 4(1), 4\u201317 (2018)","journal-title":"IEEE Trans. Signal Inf. Process. Over Netw."},{"key":"1049_CR19","unstructured":"M.A. Pathak, S. Rane, B. Raj, Multiparty differential privacy via aggregation of locally trained classifiers, in Advances in Neural Information Processing Systems, Vancouver, Canada (2010), pp. 1876\u20131884"},{"key":"1049_CR20","unstructured":"S. Gade, N.H. Vaidya, Private learning on networks. arXiv:1612.05236 (2016)"},{"key":"1049_CR21","doi-asserted-by":"crossref","unstructured":"K. Bonawitz, V. Ivanov, B. Kreuter, A. Marcedone, H.B. McMahan, S. Patel, D. Ramage, A. Segal, K. Seth, Practical secure aggregation for privacy-preserving machine learning, in Proceedings of ACM SIGSAC Conference on Computer and Communications Security, New York, USA (2017), pp. 1175\u20131191","DOI":"10.1145\/3133956.3133982"},{"issue":"4","key":"1049_CR22","first-page":"345","volume":"2017","author":"A Gasc\u00f3n","year":"2017","unstructured":"A. Gasc\u00f3n, P. Schoppmann, B. Balle, M. Raykova, J. Doerner, S. Zahur, D. Evans, Privacy-preserving distributed linear regression on high-dimensional data. Proc. Priv. Enhanc. Technol. 2017(4), 345\u2013364 (2017)","journal-title":"Proc. Priv. Enhanc. Technol."},{"key":"1049_CR23","doi-asserted-by":"crossref","unstructured":"P. Mohassel, Y. Zhang, SecureML: a system for scalable privacy-preserving machine learning, in IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA (2017), pp. 19\u201338","DOI":"10.1109\/SP.2017.12"},{"key":"1049_CR24","doi-asserted-by":"crossref","unstructured":"V. Nikolaenko, U. Weinsberg, S. Ioannidis, M. Joye, D. Boneh, N. Taft, Privacy-preserving ridge regression on hundreds of millions of records, in IEEE Symposium on Security and Privacy, Berkeley, CA, USA (2013), pp. 334\u2013348","DOI":"10.1109\/SP.2013.30"},{"key":"1049_CR25","doi-asserted-by":"crossref","unstructured":"W. Zheng, R.A. Popa, J.E. Gonzalez, I. Stoica, Helen: Maliciously secure coopetitive learning for linear models, in IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA (2019), pp. 724\u2013738","DOI":"10.1109\/SP.2019.00045"},{"key":"1049_CR26","doi-asserted-by":"crossref","unstructured":"Y. Ishai, E. Kushilevitz, R. Ostrovsky, A. Sahai, Cryptography with constant computational overhead, in Proceedings Annual ACM Symposium on Theory of Computing, Victoria British Columbia Canada (2008), pp. 433\u2013442","DOI":"10.1145\/1374376.1374438"},{"key":"1049_CR27","doi-asserted-by":"crossref","unstructured":"I. Damg\u00e5rd, Y. Ishai, M. Kr\u00f8igaard, Perfectly secure multiparty computation and the computational overhead of cryptography, in Annual International Conference on the Theory and Applications of Cryptographic Techniques, France (2010), pp. 445\u2013465","DOI":"10.1007\/978-3-642-13190-5_23"},{"key":"1049_CR28","doi-asserted-by":"crossref","unstructured":"E. Rizk, S. Vlaski, A.H. Sayed, Federated learning under importance sampling (2020). arXiv:2012.07383","DOI":"10.1109\/SPAWC48557.2020.9154327"},{"key":"1049_CR29","unstructured":"K. Avazu, Avazu\u2019s Click-Through Rate Prediction (2014). http:\/\/www.csie.ntu.edu.tw\/-cj1in\/libsvmtools\/"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-023-01049-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13634-023-01049-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-023-01049-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T23:19:56Z","timestamp":1700435996000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-023-01049-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,25]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["1049"],"URL":"https:\/\/doi.org\/10.1186\/s13634-023-01049-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2484033\/v1","asserted-by":"object"}]},"ISSN":["1687-6180"],"issn-type":[{"type":"electronic","value":"1687-6180"}],"subject":[],"published":{"date-parts":[[2023,8,25]]},"assertion":[{"value":"16 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"87"}}