一种基于区块链的个性化联邦边缘学习保护框架

doi:10.3969/j.issn.0255-8297.2026.05.003

摘要/Abstract

摘要： 针对联邦学习在边缘场景下面临的资源约束、数据异构性及安全威胁等挑战，提出一种基于区块链的个性化联邦边缘学习保护框架。旨在通过去中心化共识机制、安全压缩与个性化微调协同作用，提升对恶意客户端及Non-IID数据的鲁棒性。通过构建安全压缩与个性化微调协同机制，实现本地模型适应能力增强、通信开销降低及聚合过程鲁棒性保障。在此基础上，设计了一种融合贡献与信任的双重激励机制，并基于Raft协议整合可验证随机函数，构建VRF-VGRaft共识算法，实现候选节点筛选、随机可验证的领导者选举及多方验证组构建。在FEMNIST和CIFAR10数据集上的仿真实验表明，相较于现有方法，该框架在处理Non-IID数据及恶意节点时，能显著提升联邦学习的安全性与效率。

关键词: 区块链, 联邦学习, 共识算法, 边缘计算, 激励机制

Abstract: Federated learning in edge scenarios faces resource constraints, data heterogeneity, and security threats. This paper proposes a blockchain-based protection framework for personalized federated edge learning. The framework combines a decentralized consensus mechanism, secure compression, and personalized fine-tuning. These components jointly improve robustness to malicious clients and non-IID data. A coordination mechanism integrating secure compression and personalized fine-tuning is designed to enhance local model adaptability, reduce communication overhead, and ensure robust aggregation. A dual incentive mechanism combining contribution and trust is further proposed. Based on the Raft protocol, a verifiable random function is integrated to construct a consensus algorithm called VRF-VGRaft, enabling candidate node screening, random and verifiable leader election, and multi-party verification group construction. Simulation experiments were conducted on the FEMNIST and CIFAR10 datasets. The results show that, compared with existing methods, the framework significantly improves the security and efficiency of federated learning when handling non-IID data and malicious nodes.

Key words: blockchain, federated learning, consensus algorithm, edge computing, incentive mechanism

中图分类号:

云健, 刘涛, 高新茹, 张海玉. 一种基于区块链的个性化联邦边缘学习保护框架[J]. 应用科学学报, 2026, 44(5): 731-751.

YUN Jian, LIU Tao, GAO Xinru, ZHANG Haiyu. Blockchain-Based Protection Framework for Personalized Federated Edge Learning[J]. Journal of Applied Sciences, 2026, 44(5): 731-751.

[1] Al-Sarawi S, Anbar M, Abdullah R, et al. Internet of things market analysis forecasts, 2020–2030[C]//2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability, 2020: 449-453.
[2] Mcmahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data [C]//Artificial Intelligence and Statistics, 2017: 1273-1282.
[3] Pokhrel S R, Choi J. Federated learning with blockchain for autonomous vehicles: analysis and design challenges [J]. IEEE Transactions on Communications, 2020, 68(8): 4734-4746.
[4] Jiang J C, Kantarci B, Oktug S, et al. Federated learning in smart city sensing: challenges and opportunities [J]. Sensors, 2020, 20(21): 6230.
[5] Yao W, Zhou T, Han Y, et al. Verifiable secure aggregation scheme for privacy protection in federated learning networks [J]. Discover Computing, 2025, 28(1): 175.
[6] Sun S, Si C, Wu G, et al. Federated zero-shot learning with mid-level semantic knowledge transfer [J]. Pattern Recognition, 2024, 156: 110824.
[7] Feng Y, Guo Y, Hou Y, et al. A survey of security threats in federated learning [J]. Complex & Intelligent Systems, 2025, 11(2): 165.
[8] Orabi M M, Emam O, Fahmy H. Adapting security and decentralized knowledge enhancement in federated learning using blockchain technology: literature review [J]. Journal of Big Data, 2025, 12(1): 55.
[9] Kim H, Park J, Bennis M, et al. Blockchained on-device federated learning [J]. IEEE Communications Letters, 2019, 24(6): 1279-1283.
[10] Zhou S, Li K, Chen Y, et al. TrustBCFL: mitigating data bias in IoT through blockchain-enabled federated learning [J]. IEEE Internet of Things Journal, 2024, 11(15): 25648-25662.
[11] Jin R, Hu J, Min G, et al. Lightweight blockchain-empowered secure and efficient federated edge learning [J]. IEEE Transactions on Computers, 2023, 72(11): 3314-3325.
[12] Wang X, Xie Y, Chen X, et al. Securing federated learning with blockchain in the medical field: systematic literature review [J]. Journal of Medical Internet Research, 2026, 28: e79052.
[13] Lian Z, Wang W, Han Z, et al. Blockchain-based personalized federated learning for internet of medical things [J]. IEEE Transactions on Sustainable Computing, 2023, 8(4): 694-702.
[14] Huang C, Liu E, Wang R, et al. Personalized federated learning via directed acyclic graph based blockchain [J]. IET Blockchain, 2024, 4(1): 73-82.
[15] Yun J, Lu Y, Liu X. BCAFL: a blockchain-based framework for asynchronous federated learning protection [J]. Electronics, 2023, 12(20): 4214.
[16] Lin Y, Han S, Mao H, et al. Deep gradient compression: reducing the communication bandwidth for distributed training [PP/OL]. V3. (2020-06-23) [2026-01-20]. https://doi.org/10.48550/arXiv.1712.01887.
[17] Alistarh D, Grubic D, Li J, et al. QSGD: communication-efficient SGD via gradient quantization and encoding [J]. Advances in Neural Information Processing Systems, 2017:30.
[18] Bernstein J, Wang Y X, Azizzadenesheli K, et al. SignSGD: compressed optimisation for nonconvex problems [C]//International Conference on Machine Learning, 2018: 560-569.
[19] Kairouz P, Mcmahan H B. Advances and open problems in federated learning [J]. Foundations and Trends in Machine Learning, 2021, 14(1/2): 1-210.
[20] Vogels T, Karimireddy S P, Jaggi M. PowerSGD: practical low-rank gradient compression for distributed optimization [J]. Advances in Neural Information Processing Systems, 2019:32.
[21] Mugunthan V, Rahman R, Kagal L. Blockflow: an accountable and privacypreserving solution for federated learning [PP/OL]. V1. (2020-07-08) [2026-01-20]. https://doi.org/10.48550/arXiv.2007.03856.
[22] Xu M, Zou Z, Cheng Y, et al. SPDL: a blockchain-enabled secure and privacy-preserving decentralized learning system [J]. IEEE Transactions on Computers, 2022, 72(2): 548-558.
[23] Chen X, Feng C, Wang S. AIDFL: an information-driven anomaly detector for data poisoning in decentralized federated learning [J]. IEEE Access, 2025, 13: 50017-50031.
[24] Uddin M P, Xiang Y, Lu X, et al. Mutual information driven federated learning [J]. IEEE Transactions on Parallel and Distributed Systems, 2020, 32(7): 1526-1538.
[25] Xiao P, Cheng S, Stankovic V, et al. Averaging is probably not the optimum way of aggregating parameters in federated learning [J]. Entropy, 2020, 22(3): 314.
[26] Fallah A, Mokhtari A, Ozdaglar A. Personalized federated learning with theoretical guarantees: a model-agnostic meta-learning approach [J]. Advances in Neural Information Processing Systems, 2020, 33: 3557-3568.
[27] Chen F, Long G, Wu Z, et al. Personalized federated learning with a graph [C]//Thirty-First International Joint Conference on Artificial Intelligence, 2022: 2575-2582.
[28] Nikoloutsopoulos S, Koutsopoulos I, Titsias M K. Personalized federated learning with exact stochastic gradient descent [J]. Applied Intelligence, 2025, 55(17): 1123.
[29] Alharby M, Alssaiari A, Alateef S, et al. A quantitative analysis of the security of PoW-based blockchains [J]. Cluster Computing, 2024, 27(10): 14113-14130.
[30] Xu J, Wang C, Jia X. A survey of blockchain consensus protocols [J]. ACM Computing Surveys, 2023, 55(Suppl.13): 1-35.
[31] Abdorrahimi B, Nekouie A, Rahmani A M, et al. Blockchain technology and raft consensus for secure physician prescriptions and improved diagnoses in electronic healthcare systems [J]. Scientific Reports, 2024, 14(1): 15692.
[32] Zhou S, Ying B. Vg-Raft: an improved Byzantine fault tolerant algorithm based on raft algorithm [C]//2021 IEEE 21st International Conference on Communication Technology, 2021: 882-886.
[33] Gilad Y, Hemo R, Micali S, et al. Algorand: scaling Byzantine agreements for cryptocurrencies [C]//26th Symposium on Operating Systems Principles, 2017: 51-68.
[34] Benet J. IPFS-content addressed, versioned, P2P file system [PP/OL]. V1(2014-07-14) [2026- 01-20]. https://doi.org/10.48550/arXiv.1407.3561.
[35] Caldas S, Duddu S M K, Wu P, et al. Leaf: a benchmark for federated settings [PP/OL]. V3(2019-12-09) [2026-01-20]. https://doi.org/10.48550/arXiv.1812.01097.
[36] Li A, Sun J, Wang B, et al. LotteryFL: personalized and communication-efficient federated learning with lottery ticket hypothesis on non-IID datasets [PP/OL]. V3. (2020-08-09) [2026- 01-20]. https://doi.org/10.48550/arXiv.2008.03371.
[37] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition [C]//IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.

一种基于区块链的个性化联邦边缘学习保护框架

Blockchain-Based Protection Framework for Personalized Federated Edge Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李熙, 文斌, 王怡蓓. 基于零知识证明的可信数据质量评估[J]. 应用科学学报, 2026, 44(5): 771-786.
[2]	孟令洋, 李鹏, 孙丽, 杜剑. 基于深度强化学习的分片区块链节点多维评估和智能动态重构方案[J]. 应用科学学报, 2026, 44(5): 752-770.
[3]	郭丽, 张文杰, 潘恒, 陆思奇, 邢颖, 李坤阳, 张博伟, 斯雪明. LauHunter：一种快速高效的洗钱检测工具[J]. 应用科学学报, 2026, 44(5): 716-730.
[4]	饶芮瑞, 朱莉, 颜嘉麒. 融合大语言模型的区块链开源项目主题挖掘与演化分析[J]. 应用科学学报, 2026, 44(5): 701-715.
[5]	马小锋, 张诚, 史汶泽, 陆林. 一种面向簇分布异构的一次通信联邦聚类方法[J]. 应用科学学报, 2026, 44(5): 861-874.
[6]	李守伟, 蒋易珉, 张嘉政. 多源异质数据资产分链交易体系设计[J]. 应用科学学报, 2026, 44(3): 465-485.
[7]	斯雪明, 马硕森, 姚中原. 适用于物联网环境的多维并行区块链[J]. 应用科学学报, 2026, 44(2): 282-296.
[8]	伊华伟, 宋仕玺, 王艳飞, 白思怡. 融合图神经网络和深度图聚类的联邦推荐算法[J]. 应用科学学报, 2026, 44(1): 83-96.
[9]	陈强斌, 姚中原, 田浩, 斯雪明. BalChain：一种基于信誉与负载的分片区块链系统[J]. 应用科学学报, 2025, 43(5): 863-876.
[10]	何旭荣, 方有轩, 郑旭晓, 辛艳双. 基于预言机组件技术的跨链系统研究与实现[J]. 应用科学学报, 2025, 43(4): 630-642.
[11]	潘璇, 张抗抗, 程澳. 一种基于区块链的数据要素精准授权机制[J]. 应用科学学报, 2025, 43(4): 600-616.
[12]	张壮, 邹义林, 林泽鹏, 刘家圆, 訾宗青, 谭良, 佘堃. 通用区块链跨链交易形式化定义及实例验证分析[J]. 应用科学学报, 2025, 43(4): 559-585.
[13]	刘丽丽, 时忆杰, 秦素娟. 基于机器学习的智能合约漏洞检测技术[J]. 应用科学学报, 2025, 43(4): 541-558.
[14]	杨哲, 任艳丽, 钟月歌, 冯国瑞. 可验证的隐私保护个性化联邦学习[J]. 应用科学学报, 2025, 43(3): 463-474.
[15]	兰亚杰, 马自强, 苗莉, 胡富森. 基于区块链的图像数字版权保护系统[J]. 应用科学学报, 2025, 43(2): 315-333.