{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T20:34:12Z","timestamp":1775421252187,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:00:00Z","timestamp":1677110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:00:00Z","timestamp":1677110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172436"],"award-info":[{"award-number":["62172436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province of China","award":["2020JQ-492"],"award-info":[{"award-number":["2020JQ-492"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To ensure no private information is leaked in the aggregation phase in federated learning (FL), many frameworks use homomorphic encryption (HE) to mask local model updates. However, the heavy overheads of these frameworks make them unsuitable for cross-device FL, where the clients are a huge number of mobile and edge devices with limited computing resources. Even worse, some of them also fail to manage the dynamic changes of clients. To overcome these shortcomings, we propose a threshold multi-key HE scheme tMK-CKKS and design an efficient and robust privacy-preserving FL framework. Robustness means that our framework allows clients to join in or drop out during the training process. Besides, because our tMK-CKKS scheme can pack multiple messages in a single ciphertext, our framework significantly reduces the computation and communication overhead. Moreover, the threshold mechanism in tMK-CKKS ensures that our framework can resist collusion attacks between the server and no more than <jats:italic>t<\/jats:italic> (threshold value) curious internal clients. Finally, we implement our framework in FedML and conduct extensive experiments to evaluate our framework. Utility evaluations on 6 benchmark datasets show that our framework can protect privacy without sacrificing the model accuracy. Efficiency evaluations on 4 typical deep learning models demonstrate that: our framework can speed up the computation by at least 1.21<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\times $$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u00d7<\/mml:mo>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> over xMK-CKKS-based framework, 15.84<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\times $$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u00d7<\/mml:mo>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> over Batchcrypt-based framework, and 20.30<jats:inline-formula><jats:alternatives><jats:tex-math>$$\\times $$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u00d7<\/mml:mo>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> over CRT-Paillier-based framework. Our framework can reduce the communication burden by at least 8.61 MB over Batchcrypt-based framework, 35.36 MB over xMK-CKKS-based framework and 42.58 MB over CRT-Paillier-based framework. The advantages in both computation and communication expand with the size of deep learning models.<\/jats:p>","DOI":"10.1007\/s40747-023-00978-9","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T10:02:31Z","timestamp":1677146551000},"page":"4923-4937","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["A efficient and robust privacy-preserving framework for cross-device federated learning"],"prefix":"10.1007","volume":"9","author":[{"given":"Weidong","family":"Du","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3009-279X","authenticated-orcid":false,"given":"Min","family":"Li","sequence":"additional","affiliation":[]},{"given":"Liqiang","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yiliang","family":"Han","sequence":"additional","affiliation":[]},{"given":"Tanping","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Xiaoyuan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"978_CR1","unstructured":"Data61 (2013) Python-Paillier. https:\/\/github.com\/data61\/python-paillier"},{"key":"978_CR2","unstructured":"HEAAN (2018). https:\/\/github.com\/snucrypto\/HEAAN"},{"key":"978_CR3","unstructured":"FedML (2020) A Research Library and Benchmark for Federated Machine Learning. https:\/\/fedml.ai\/"},{"key":"978_CR4","unstructured":"Boost C++ Libraries (2021). https:\/\/www.boost.org\/"},{"key":"978_CR5","doi-asserted-by":"publisher","unstructured":"Asoodeh S, Chen WN, Calmon FP, Ozgur A (2021) Differentially Private Federated Learning: An Information-Theoretic Perspective. In: 2021 IEEE International Symposium on Information Theory (ISIT). IEEE, Melbourne, Australia, pp 344\u2013349. https:\/\/doi.org\/10.1109\/ISIT45174.2021.9518124","DOI":"10.1109\/ISIT45174.2021.9518124"},{"key":"978_CR6","doi-asserted-by":"publisher","unstructured":"Barker E, Chen L, Roginsky A, Vassilev A, Davis R, Simon S (2019) Recommendation for pair-wise key establishment using integer factorization cryptography. Tech. Rep. NIST SP 800-56Br2, National Institute of Standards and Technology, Gaithersburg, MD. https:\/\/doi.org\/10.6028\/NIST.SP.800-56Br2","DOI":"10.6028\/NIST.SP.800-56Br2"},{"key":"978_CR7","doi-asserted-by":"publisher","unstructured":"Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, Ramage D, Segal A, Seth K (2017) Practical Secure Aggregation for Privacy-Preserving Machine Learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. ACM, Dallas Texas USA, pp 1175\u20131191. https:\/\/doi.org\/10.1145\/3133956.3133982","DOI":"10.1145\/3133956.3133982"},{"key":"978_CR8","doi-asserted-by":"crossref","unstructured":"Cheng A, Wang P, Zhang XS, Cheng J (2022) Differentially Private Federated Learning With Local Regularization and Sparsification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10122\u201310131","DOI":"10.1109\/CVPR52688.2022.00988"},{"issue":"6","key":"978_CR9","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/MIS.2021.3082561","volume":"36","author":"K Cheng","year":"2021","unstructured":"Cheng K, Fan T, Jin Y, Liu Y, Chen T, Papadopoulos D, Yang Q (2021) SecureBoost: A Lossless Federated Learning Framework. IEEE Intell Syst 36(6):87\u201398. https:\/\/doi.org\/10.1109\/MIS.2021.3082561","journal-title":"IEEE Intell Syst"},{"key":"978_CR10","unstructured":"Cheon JH, Kim A, Kim M, Song Y (2016) Homomorphic Encryption for Arithmetic of Approximate Numbers. Tech. Rep. 421"},{"key":"978_CR11","unstructured":"Geyer RC, Klein T, Nabi M (2018) Differentially Private Federated Learning: A Client Level Perspective. arXiv:1712.07557 [cs, stat]"},{"key":"978_CR12","unstructured":"Kadhe S, Rajaraman N, Koyluoglu OO, Ramchandran K (2020) FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning"},{"key":"978_CR13","unstructured":"Kairouz P (2019) McMahan: Advances and Open Problems in Federated Learning. arXiv:1912.04977 [cs, stat]"},{"key":"978_CR14","unstructured":"Kone\u010dn\u00fd J, McMahan HB, Ramage D, Richt\u00e1rik P (2016) Federated Optimization: Distributed Machine Learning for On-Device Intelligence. arXiv:1610.02527 [cs]"},{"key":"978_CR15","unstructured":"Kone\u010dn\u00fd J, McMahan HB, Yu FX, Richt\u00e1rik P, Suresh AT, Bacon D (2017) Federated Learning: Strategies for Improving Communication Efficiency. arXiv:1610.05492 [cs]"},{"key":"978_CR16","doi-asserted-by":"publisher","first-page":"106854","DOI":"10.1016\/j.cie.2020.106854","volume":"149","author":"L Li","year":"2020","unstructured":"Li L, Fan Y, Tse M, Lin KY (2020) A review of applications in federated learning. Computers & Industrial Engineering 149:106854. https:\/\/doi.org\/10.1016\/j.cie.2020.106854","journal-title":"Computers & Industrial Engineering"},{"key":"978_CR17","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-030-17277-0_9","volume-title":"Policy-Based Autonomic Data Governance","author":"C Liu","year":"2019","unstructured":"Liu C, Chakraborty S, Verma D (2019) Secure Model Fusion for Distributed Learning Using Partial Homomorphic Encryption. In: Calo S, Bertino E, Verma D (eds) Policy-Based Autonomic Data Governance, vol 11550. Springer International Publishing, Cham, pp 154\u2013179. https:\/\/doi.org\/10.1007\/978-3-030-17277-0_9"},{"issue":"4","key":"978_CR18","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1007\/s10115-022-01664-x","volume":"64","author":"J Liu","year":"2022","unstructured":"Liu J, Huang J, Zhou Y, Li X, Ji S, Xiong H, Dou D (2022) From Distributed Machine Learning to Federated Learning: A Survey. Knowl Inf Syst 64(4):885\u2013917. https:\/\/doi.org\/10.1007\/s10115-022-01664-x","journal-title":"Knowl Inf Syst"},{"issue":"4","key":"978_CR19","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/MIS.2020.2988525","volume":"35","author":"Y Liu","year":"2020","unstructured":"Liu Y, Kang Y, Xing C, Chen T, Yang Q (2020) A Secure Federated Transfer Learning Framework. IEEE Intell Syst 35(4):70\u201382. https:\/\/doi.org\/10.1109\/MIS.2020.2988525","journal-title":"IEEE Intell Syst"},{"key":"978_CR20","first-page":"1","volume-title":"Advances in Cryptology - EUROCRYPT 2010","author":"V Lyubashevsky","year":"2010","unstructured":"Lyubashevsky V, Peikert C, Regev O (2010) On ideal lattices and learning with errors over rings. In: Gilbert H (ed) Advances in Cryptology - EUROCRYPT 2010. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 1\u201323"},{"key":"978_CR21","unstructured":"Lyubashevsky V, Peikert C, Regev O (2012) On Ideal Lattices and Learning with Errors Over Rings. Tech. Rep. 230"},{"key":"978_CR22","doi-asserted-by":"crossref","unstructured":"Ma J, Naas SA, Sigg S, Lyu X (2021) Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryption. arXiv:2104.06824 [cs]","DOI":"10.1002\/int.22818"},{"key":"978_CR23","unstructured":"Mathews SM, Assefa SA (2022) Federated Learning: Balancing the Thin Line Between Data Intelligence and Privacy. Tech. Rep. arXiv:2204.13697"},{"key":"978_CR24","unstructured":"McMahan HB, Moore E, Ramage D, Hampson S, y\u00a0Arcas BA (2016) Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv:1602.05629 [cs]"},{"key":"978_CR25","unstructured":"McMahan HB, Ramage D, Talwar K, Zhang L (2018) Learning Differentially Private Recurrent Language Models. In: arXiv:1710.06963 [Cs]"},{"key":"978_CR26","doi-asserted-by":"crossref","unstructured":"Phong LT, Aono Y, Hayashi T, Wang L, Moriai S (2017) Privacy-Preserving Deep Learning via Additively Homomorphic Encryption. Tech. Rep. 715","DOI":"10.1007\/978-981-10-5421-1_9"},{"key":"978_CR27","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1109\/TSP.2022.3153135","volume":"70","author":"K Pillutla","year":"2022","unstructured":"Pillutla K, Kakade SM, Harchaoui Z (2022) Robust Aggregation for Federated Learning. IEEE Trans Signal Process 70:1142\u20131154. https:\/\/doi.org\/10.1109\/TSP.2022.3153135","journal-title":"IEEE Trans Signal Process"},{"key":"978_CR28","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1145\/359168.359176","volume":"22","author":"A Shamir","year":"1979","unstructured":"Shamir A (1979) How to Share a Secret. Commun ACM 22:612\u2013613. https:\/\/doi.org\/10.1145\/359168.359176","journal-title":"Commun ACM"},{"key":"978_CR29","doi-asserted-by":"publisher","unstructured":"Shokri R, Shmatikov V (2015) Privacy-Preserving Deep Learning. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1310\u20131321. ACM, Denver Colorado USA. https:\/\/doi.org\/10.1145\/2810103.2813687","DOI":"10.1145\/2810103.2813687"},{"key":"978_CR30","doi-asserted-by":"publisher","unstructured":"So J, Guler B, Avestimehr AS (2020) Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning. https:\/\/doi.org\/10.48550\/arXiv.2002.04156","DOI":"10.48550\/arXiv.2002.04156"},{"key":"978_CR31","unstructured":"Stevnes T, Skalka C, Vincent C (2022) Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors. In: 31st USENIX Security Symposium (USENIX Security 22)"},{"key":"978_CR32","doi-asserted-by":"crossref","unstructured":"Truex S, Baracaldo N, Anwar A, Steinke T, Ludwig H, Zhang R, Zhou Y (2019) A Hybrid Approach to Privacy-Preserving Federated Learning. arXiv:1812.03224 [cs, stat]","DOI":"10.1145\/3338501.3357370"},{"key":"978_CR33","doi-asserted-by":"crossref","unstructured":"Wu C, Wu F, Cao Y, Huang Y, Xie X (2021) FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation","DOI":"10.1038\/s41467-022-30714-9"},{"key":"978_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIFS.2019.2929409","volume":"PP","author":"G Xu","year":"2019","unstructured":"Xu G, Li H, Liu S, Yang K, Lin X (2019) VerifyNet: Secure and Verifiable Federated Learning. IEEE Trans Inf Forensics Secur PP:1\u20131. https:\/\/doi.org\/10.1109\/TIFS.2019.2929409","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"6","key":"978_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3460427","volume":"54","author":"X Yin","year":"2021","unstructured":"Yin X, Zhu Y, Hu J (2021) A Comprehensive Survey of Privacy-preserving Federated Learning: A Taxonomy, Review, and Future Directions. ACM Comput Surv 54(6):1\u201336. https:\/\/doi.org\/10.1145\/3460427","journal-title":"ACM Comput Surv"},{"key":"978_CR36","doi-asserted-by":"publisher","unstructured":"Yu B, Mao W, Lv Y, Zhang C, Xie Y (2022) A survey on federated learning in data mining. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 12. https:\/\/doi.org\/10.1002\/widm.1443","DOI":"10.1002\/widm.1443"},{"key":"978_CR37","unstructured":"Zhang C, Li S, Xia J, Wang W, Yan F, Liu Y (2020) BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning. In: 2020 USENIX Annual Technical Conference. USENIX Association, pp 493\u2013506"},{"key":"978_CR38","doi-asserted-by":"publisher","unstructured":"Zhang J, Chen B, Yu S, Deng H (2019) PEFL: A Privacy-Enhanced Federated Learning Scheme for Big Data Analytics. In: 2019 IEEE Global Communications Conference (GLOBECOM), pp 1\u20136. https:\/\/doi.org\/10.1109\/GLOBECOM38437.2019.9014272","DOI":"10.1109\/GLOBECOM38437.2019.9014272"},{"key":"978_CR39","doi-asserted-by":"publisher","unstructured":"Zhang X, Fu A, Wang H, Zhou C, Chen Z (2020) A Privacy-Preserving and Verifiable Federated Learning Scheme. In: ICC 2020 - 2020 IEEE International Conference on Communications (ICC), pp 1\u20136. IEEE, Dublin, Ireland. https:\/\/doi.org\/10.1109\/ICC40277.2020.9148628","DOI":"10.1109\/ICC40277.2020.9148628"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-00978-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-00978-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-00978-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T17:13:45Z","timestamp":1695402825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-00978-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,23]]},"references-count":39,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["978"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-00978-9","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,23]]},"assertion":[{"value":"22 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 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":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}