计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (6): 446-459.doi: 10.11896/jsjkx.250600089

• 信息安全 • 上一篇    

基于多密钥同态加密的边缘联邦学习隐私保护方案

李瑞芮1,2, 郭瑞1,2, 张应辉1,2, 李雪雷3, 刘光军4   

  1. 1 西安邮电大学网络空间安全学院 西安 710121
    2 西安邮电大学无线网络安全技术国家工程研究中心 西安 710121
    3 浪潮(北京)电子信息产业有限公司 北京 100089
    4 西安文理学院信息工程学院 西安 710065
  • 收稿日期:2025-06-12 修回日期:2025-09-10 出版日期:2026-06-15 发布日期:2026-06-09
  • 通讯作者: 郭瑞(guorui@xupt.edu.cn)
  • 作者简介:(lr_r26@163.com)
  • 基金资助:
    国家密码科学基金(2025NCSF02037);国家自然科学基金(62072369);北京市科技新星计划(20230484455);陕西省重点研发计划(2020ZDLGY08-04);陕西省创新能力支持计划(2020KJXX-052);陕西省自然科学基金一般项目(2024JC-YBMS-545,2024JC-YBMS-557);陕西省高校青年创新团队(23JP160,24JP180,25JP178);西安市科技计划项目(23KGDW0018-2023)

Edge Federated Learning Privacy Protection Scheme Based on Multi-key Homomorphic Encryption

LI Ruirui1,2, GUO Rui1,2, ZHANG Yinghui1,2, LI Xuelei3, LIU Guangjun4   

  1. 1 School of Cyber Security,Xi'an University of Posts and Telecommunications,Xi'an 710121,China
    2 National Engineering Research Center for Secured Wireless,Xi'an University of Posts and Telecommunications,Xi'an 710121,China
    3 IEIT SYSTEMS(Beijing) Co.,Ltd.,Beijing 100089,China
    4 School of Information Engineering,Xi'an University,Xi'an 710065,China
  • Received:2025-06-12 Revised:2025-09-10 Published:2026-06-15 Online:2026-06-09
  • About author:LI Ruirui,born in 2001,postgraduate.Her main research interests include homomorphic encryption,and so on.
    GUO Rui,born in 1984,Ph.D,professor,is a member of CCF(No.E3529M).His main research interests include privacy preserving,blockchain,and so on.
  • Supported by:
    National Cryptologic Science Fundation of China(2025NCSF02037),National Natural Science Foundation of China(62072369),Beijing Nova Program(20230484455),Shaanxi Provincial Key Research and Development Program(2020ZDLGY08-04),Innovation Capacity Support Program of Shaanxi Province(2020KJXX-052),General Program of Natural Science Foundation of Shaanxi Province(2024JC-YBMS-545,2024JC-YBMS-557),Youth Innovation Team of Shaanxi Universities(23JP160,24JP180,25JP178) and Science and Technology Program of Xi'an(23KGDW0018-2023).

PDF (PC)

81

摘要： 联邦学习可以使用户在不共享原始数据的前提下,通过聚合本地模型更新参数来协同训练一个机器学习模型。然而,传统联邦学习中存在因过度依赖中央服务器而导致的单点故障、隐私泄露及通信瓶颈等问题。为此,提出一种去中心化的多边缘分布式联邦学习隐私保护方案。通过设计基于聚合多密钥同态加密方案(Aggregation Multi-Key Cheon-Kim-Kim-Song,AMK-CKKS)的本地模型聚合机制,实现对数据拥有者原始数据的隐私保护功能。此外,利用RingAllreduce算法构建分布式全局模型聚合框架,边缘服务器代替中央服务器进行全局模型聚合,以有效降低通信负载并消除对中心节点的依赖。同时,引入区块链和SG-PBFT共识机制,在确保模型更新参数可审计性的前提下,使节点快速达成共识,保证运行过程中诚实节点的安全性。安全性分析表明,所提方案不仅能确保模型更新参数的隐私性,而且能够抵抗k<(n－2)个参与方之间的合谋攻击;与相关方案相比,所提方案的模型准确度损失不超过3%,且通信开销降低约76%。

关键词: 联邦学习, 隐私保护, 多密钥同态加密, 边缘计算, 区块链

Abstract: Federated learning allows users to collaboratively train a machine learning model by aggregating local model updates without sharing raw data.However,traditional federated learning faces issues such as reliance on a central server leading to single points of failure,privacy leakage,and communication bottlenecks.To address these problems,this paper proposes a decentralized multi-edge distributed federated learning privacy protection scheme.A local model aggregation mechanism based on Aggregation Multi-Key Cheon-Kim-Kim-Song(AMK-CKKS)is designed,it implements privacy protection for the raw data owned by data owners.Additionally,a distributed global model aggregation framework is constructed using the RingAllreduce algorithm,where edge servers replace the central server for global model aggregation,effectively reducing communication load and eliminating dependence on central nodes.Furthermore,the introduction of blockchain and the SG-PBFT consensus mechanism ensures that model update parameters are auditable and allows nodes to reach consensus quickly while ensuring the security of honest nodes during operation.Security analysis indicates that this scheme not only ensures the privacy of the model update parameters but also resists collusion attacks involving up tok<(n－2) participants.Moreover,compared to related schemes,the accuracy loss of the proposed model does not exceed 3%,and communication overhead is reduced by approximately 76%.

Key words: Federated learning, Privacy protection, Multi-key homomorphic encryption, Edge computing, Blockchain

中图分类号: 

  • TP309
[1]ZHANG C,XIE Y,BAI H,et al.A survey on federated learning[J].Knowledge-Based Systems,2021,216:106775.
[2]MCMAHAN B,MOORE E,RAMAGE D,et al.Communica-tion-efficient learning of deep networks from decentralized data[C]//Artificial Intelligence and Statistics.PMLR,2017:1273-1282.
[3]MELIS L,SONG C,DE CRISTOFARO E,et al.Exploiting unintended feature leakage in collaborative learning[C]//2019 IEEE Symposium on Security and Privacy(SP).IEEE,2019:691-706.
[4]SONG M,WANG Z,ZHANG Z,et al.Analyzing user-level privacy attack against federated learning[J].IEEE Journal on Selected Areas in Communications,2020,38(10):2430-2444.
[5]GHOLAMI A,TORKZABAN N,BARAS J S.Trusted decentralized federated learning[C]//2022 IEEE 19th Annual Consumer Communications & Networking Conference(CCNC).IEEE,2022:1-6.
[6]LIAN X,ZHANG C,ZHANG H,et al.Can decentralized algorithms outperform centralized algorithms?a case study for decentralized parallel stochastic gradient descent[J].arXiv:1705.09056,2017.
[7]QU Y,XU C,GAO L,et al.Fl-sec:Privacy-preserving decen-tralized federated learning using signsgd for the internet of artificially intelligent things[J].IEEE Internet of Things Magazine,2022,5(1):85-90.
[8]ZHU W,SHI L,LI J,et al.Trustworthy Blockchain-Assisted Federated Learning:Decentralized Reputation Management and Performance Optimization[J].IEEE Internet of Things Journal,2025,12(3):2890-2905.
[9]XU L,CHEN Y,CHEN Y,et al.Swarm Learning for temporal and spatial series data in energy systems:A decentralized collaborative learning design based on blockchain[J].Applied Energy,2025,381:125053.
[10]TIAN Y,WANG S,XIONG J,et al.Robust and privacy-preserving decentralized deep federated learning training:Focusing on digital healthcare applications[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2024,21(4):890-901.
[11]GENTRY C,HALEVI S.Implementing gentry's fully-homo-morphic encryption scheme[C]//Annual International Confe-rence on the Theory and Applications of Cryptographic Techniques.Berlin:Springer,2011:129-148.
[12]SMART N P,VERCAUTEREN F.Fully homomorphic SIMD operations[J].Designs,Codes and Crytography,2014,71(1):57-81.
[13]BRAKERSKI Z,VAIKUNTANATHAN V.Efficient fully homomorphic encryption from(standard) LWE[J].SIAM Journal on Computing,2014,43(2):831-871.
[14]BRAKERSKI Z,GENTRY C,VAIKUNTANATHAN V.(Le-veled) fully homomorphic encryption without bootstrapping[C]//Proceedings of the 3rd Innovations in Theoretical Computer Science Conference.2012:309-325.
[15]BRAKERSKI Z.Fully homomorphic encryption without modulus switching from classical GapSVP[C]//Annual Cryptology Conference.Berlin:Springer,2012:868-886.
[16]FAN J,VERCAUTEREN F.Somewhat practical fully homo-morphic encryption[J].Cryptology ePrint Archive,2012,2012:144.
[17]GENTRY C,SAHAI A,WATERS B.Homomorphic encryption from learning with errors:Conceptually-simpler,asymptotically-faster,attribute-based[C]//Advances in Cryptology-CRYPTO 2013:33rd Annual Cryptology Conference,Santa Barbara,CA,USA,August 18-22,2013.Proceedings,Part I.Berlin:Springer,2013:75-92.
[18]CHEON J H,KIM A,KIM M,et al.Homomorphic encryption for arithmetic of approximate numbers[C]//Advances in Cryptology-ASIACRYPT 2017:23rd International Conference on the Theory and Applications of Cryptology and Information Security,Hong kong,China,December 3-7,2017,proceedings,part i 23.Springer International Publishing,2017:409-437.
[19]CHEON J H,HAN K,KIM A,et al.Bootstrapping for approximate homomorphic encryption[C]//Advances in Cryptology-EUROCRYPT 2018:37th Annual International Conference on the Theory and Applications of Cryptographic Techniques,Tel Aviv,Israel,April 29-May 3,2018 Proceedings,Part I 37.Springer International Publishing,2018:360-384.
[20]LÓPEZ-ALT A,TROMER E,VAIKUNTANATHAN V.On-the-fly multiparty computation on the cloud via multikey fully homomorphic encryption[C]//Proceedings of the Forty-fourth Annual ACM Symposium on Theory of Computing.2012:1219-1234.
[21]MUKHERJEE P,WICHS D.Two round multiparty computa-tion via multi-key FHE[C]//Advances in Cryptology-EUROCRYPT 2016:35th Annual International Conference on the Theory and Applications of Cryptographic Techniques,Vienna,Austria,May 8-12,2016,Proceedings,Part II 35.Berlin:Sprin-ger,2016:735-763.
[22]CHEN L,ZHANG Z,WANG X.Batched multi-hop multi-key FHE from ring-LWE with compact ciphertext extension[C]//Theory of Cryptography:15th International Conference(TCC 2017).Baltimore,MD,USA,Springer International Publishing,2017:597-627.
[23]CHEN H,CHILLOTTI I,SONG Y.Multi-key homomorphicencryption from TFHE[C]//Advances in Cryptology-ASIACRYPT 2019:25th International Conference on the Theory and Application of Cryptology and Information Security,Kobe,Japan,December 8-12,2019,Proceedings,Part II 25.Springer International Publishing,2019:446-472.
[24]CHEN H,DAI W,KIM M,et al.Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference[C]//Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security.2019:395-412.
[25]WEN J M,LIU Q,CHEN J,et al.Research Current Status and Challenges of Fully Homomorphic Cryptography Based on Learning with Errors [J].Cyber Security,2024,24(9):1328-1351.
[26]CASTRO M,LISKOV B.Practical byzantine fault tolerance[C]//OsDI.1999,99(1999):173-186.
[27]AMARI S.Backpropagation and stochastic gradient descentmethod[J].Neurocomputing,1993,5(4/5):185-196.
[28]CAI Y,DING W,XIAO Y,et al.Secfed:A secure and efficient federated learning based on multi-key homomorphic encryption[J].IEEE Transactions on Dependable and Secure Computing,2023,21(4):3817-3833.
[29]AONO Y,HAYASHI T,WANG L,et al.Privacy-preservingdeep learning via additively homomorphic encryption[J].IEEE Transactions on Information Forensics and Security,2017,13(5):1333-1345.
[30]ZHANG Q,JING S,ZHAO C,et al.Efficient federated learning framework based on multi-key homomorphic encryption[C]//Proceedings of the International Conference on P2P,Parallel,Grid,Cloud and Internet Computing.Springer,2022:88-105.
[31]WU Z,SONG L T,LI X L.A Communication-Efficient Decentralized Hierarchical Federated Learning Architecture [J].Computer Applications Research,2025,42(5):1325-1330.
[32]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,2002,86(11):2278-2324.
[33]KRIZHEVSKY A,HINTON G.Learning multiple layers of features from tiny images[J].Handbook of Systemic Autoimmune Diseases,2009,1(4):1-60.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发