基于区块链的联邦学习系统方案研究综述

doi:10.3778/j.issn.1002-8331.2410-0227

摘要/Abstract

摘要： 联邦学习允许多个参与方在保护数据隐私的同时共同训练模型，并广泛应用于如医疗健康、智能城市等诸多领域，为打破“数据孤岛”现象做出了重要贡献。然而，在实际应用中联邦学习存在单点故障、易受恶意攻击和数据隐私泄露等问题。为此，以具有去中心化、不可篡改和高透明度特点的区块链技术为联邦学习提供安全的数据交换平台，但集成后的架构仍然存在缺乏有效激励机制、计算存储成本高、缺乏恶意模型检测机制等问题。通过深入调研与探索基于区块链的联邦学习体系的潜力与挑战，从现有的不同框架与技术存在的问题入手，阐述了为提高整个系统的效率、安全性和公平性，对架构中的共识机制、隐私保护方案、网络安全措施、激励机制、安全聚合方法等方面的优化和改进；阐述了智能合约在自动化执行、贡献评估和奖励分配中的关键作用。最后，总结在客户端选择、数据异质化处理、隐私保护、奖励分配和区块链痛点等方面的挑战，并对未来的研究方向进行了展望。

关键词: 去中心化联邦学习, 区块链, 隐私保护, 激励机制, 智能合约

Abstract: Federated learning enables multiple participants to collaboratively train models while protecting data privacy, and it has been widely applied in various fields such as healthcare and smart cities, making significant contributions to breaking the“data silo”phenomenon. However, in practical applications, federated learning faces issues such as single points of failure, susceptibility to malicious attacks, and data privacy breaches. To address these, researchers have considered leveraging blockchain technology, which is characterized by decentralization, immutability, and high transparency, to provide a secure data exchange platform for federated learning. However, the integrated architecture still encounters challenges such as the lack of effective incentive mechanisms, high computational and storage costs, and the absence of malicious model detection mechanisms. Through in-depth research and exploration of the potential and challenges of blockchain-based federated learning systems, this paper discusses the optimization and improvement of consensus mechanisms, privacy protection schemes, network security measures, incentive mechanisms, and secure aggregation methods within the architecture, starting from the existing problems in different frameworks and technologies. Subsequently, the paper elaborates on the key role of smart contracts in automated execution, contribution assessment, and reward distribution. Finally, it identifies challenges in client selection, data heterogeneity processing, privacy protection, reward distribution, and blockchain pain points, and provides an outlook on future research directions.

Key words: decentralized federated learning, blockchain, privacy protection, incentive mechanism, smart contract

郭思昀, 李雷孝, 杜金泽, 林浩. 基于区块链的联邦学习系统方案研究综述[J]. 计算机工程与应用, 2025, 61(15): 36-53.

GUO Siyun, LI Leixiao, DU Jinze, LIN Hao. Survey of Blockchain-Based Federated Learning System Schemes[J]. Computer Engineering and Applications, 2025, 61(15): 36-53.

参考文献

[1] OKTIAN Y E, LEE S G. Blockchain-based federated learning system: a survey on design choices[J]. Sensors, 2023, 23(12): 5658.
[2] HALLAJI E, RAZAVI-FAR R, SAIF M, et al. Decentralized federated learning: a survey on security and privacy[J]. IEEE Transactions on Big Data, 2024, 10(2): 194-213.
[3] ALI S, LI Q M, YOUSAFZAI A. Blockchain and federated learning-based intrusion detection approaches for edge-enabled industrial IoT networks: a survey[J]. Ad Hoc Networks, 2024, 152: 103320.
[4] ZHANG H R, JIANG S, XUAN S C. Decentralized federated learning based on blockchain: concepts, framework, and challenges[J]. Computer Communications, 2024, 216: 140-150.
[5] ZHU J C, CAO J N, SAXENA D, et al. Blockchain-empowered federated learning: challenges, solutions, and future dire-ctions[J]. ACM Computing Surveys, 2023, 55(11): 1-31.
[6] TANG Y M, ZHANG Y T, NIU T, et al. A survey on blockchain-based federated learning: categorization, application and analysis[J]. Computer Modeling in Engineering and Sciences, 2024, 139(3): 2451-2477.
[7] MCMAHAN B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[C]//Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017: 1273-1282.
[8] 段昕汝, 陈桂茸, 陈爱网, 等. 联邦学习中的信息安全问题研究综述[J]. 计算机工程与应用, 2024, 60(3): 61-77.
DUAN X R, CHEN G R, CHEN A W, et al. Review of research on information security in federated learning[J]. Computer Engineering and Applications, 2024, 60(3): 61-77.
[9] WANG Z, HU Q J A P A. Blockchain-based federated learning: a comprehensive survey[J]. arXiv:2110.02182, 2021.
[10] FENG L, YANG Z X, GUO S Y, et al. Two-layered blockchain architecture for federated learning over the mobile edge network[J]. IEEE Network, 2022, 36(1): 45-51.
[11] FENG L, ZHAO Y Q, GUO S Y, et al. BAFL: a blockchain-based asynchronous federated learning framework[J]. IEEE Transactions on Computers, 2022, 71(5): 1092-1103.
[12] LI J, SHAO Y M, WEI K, et al. Blockchain assisted decentralized federated learning (BLADE-FL): performance analysis and resource allocation[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(10): 2401-2415.
[13] CHE C J, LI X L, CHEN C, et al. A decentralized federated learning framework via committee mechanism with convergence guarantee[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(12): 4783-4800.
[14] CHEN H, ALI ASIF S, PARK J, et al. Robust blockchained federated learning with model validation and proof-of-stake inspired consensus[J]. arXiv:2101.03300, 2021.
[15] LI Y Z, CHEN C, LIU N, et al. A blockchain-based decentralized federated learning framework with committee consensus[J]. IEEE Network: the Magazine of Global Internetworking, 2021, 35(1): 234-241.
[16] ULLAH I, DENG X H, PEI X J, et al. A verifiable and privacy-preserving blockchain-based federated learning approach[J]. Peer-to-Peer Networking and Applications, 2023, 16(5): 2256-2270.
[17] LIU S, WANG X, HUI L S, et al. Blockchain-based decentralized federated learning method in edge computing environment[J]. Applied Sciences, 2023, 13(3): 1677.
[18] HAMOUDA D, FERRAG M A, BENHAMIDA N, et al. PPSS: a privacy-preserving secure framework using blockchain-enabled federated deep learning for Industrial IoTs[J]. Pervasive and Mobile Computing, 2023, 88: 101738.
[19] JIN R, HU J, MIN G Y, et al. Lightweight blockchain-empowered secure and efficient federated edge learning[J]. IEEE Transactions on Computers, 2023, 72(11): 3314-3325.
[20] LEI Z Q, GAI K K, YU J, et al. Efficiency-enhanced blockchain-based client selection in heterogeneous federated learning[C]//Proceedings of the 2023 IEEE International Conference on Blockchain. Piscataway: IEEE, 2023: 289-296.
[21] LI Z Y, LIU J, HAO J L, et al. CrowdSFL: a secure crowd computing framework based on blockchain and federated learning[J]. Electronics, 2020, 9(5): 773.
[22] CHEN L M, ZHAO D H, TAO L P, et al. A credible and fair federated learning framework based on blockchain[J]. IEEE Transactions on Artificial Intelligence, 2025, 6(2): 301-316.
[23] CHAKRABORTY S, CHAKRABORTY S. Proof of federated training: accountable cross-network model training and inference[C]//Proceedings of the 2022 IEEE International Conference on Blockchain and Cryptocurrency. Piscataway: IEEE, 2022: 1-9.
[24] CHHETRI B, GOPALI S, OLAPOJOYE R, et al. A survey on blockchain-based federated learning and data privacy[C]//Proceedings of the 2023 IEEE 47th Annual Computers, Software, and Applications Conference. Piscataway: IEEE, 2023: 1311-1318.
[25] QU Y Y, POKHREL S R, GARG S, et al. A blockchained federated learning framework for cognitive computing in industry 4.0 networks[J]. IEEE Transactions on Industrial Informatics, 2021, 17(4): 2964-2973.
[26] SHAYAN M, FUNG C, YOON C J M, et al. Biscotti: a blockchain system for private and secure federated learning[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32(7): 1513-1525.
[27] QI Y H, HOSSAIN M S, NIE J T, et al. Privacy-preserving blockchain-based federated learning for traffic flow prediction[J]. Future Generation Computer Systems, 2021, 117: 328-337.
[28] CHEN B W, ZENG H H, XIANG T, et al. ESB-FL: efficient and secure blockchain-based federated learning with fair payment[J]. IEEE Transactions on Big Data, 2024, 10(6): 761-774.
[29] QU Y Y, GAO L X, XIANG Y, et al. FedTwin: blockchain-enabled adaptive asynchronous federated learning for digital twin networks[J]. IEEE Network, 2022, 36(6): 183-190.
[30] NING R, WANG C G, LI X, et al. BlockFed: a high-performance and trustworthy blockchain-based federated learning framework[C]//Proceedings of the IEEE Conference on Global Communications (IEEE GLOBECOM)-Intelligent Communications for Shared Prosperity. Piscataway: IEEE, 2023: 892-897.
[31] ZHAO Y, ZHAO J, JIANG L S, et al. Privacy-preserving blockchain-based federated learning for IoT devices[J]. IEEE Internet of Things Journal, 2021, 8(3): 1817-1829.
[32] ARACHCHIGE P C M, BERTOK P, KHALIL I, et al. A trustworthy privacy preserving framework for machine learning in industrial IoT systems[J]. IEEE Transactions on Industrial Informatics, 2020, 16(9): 6092-6102.
[33] SALIM S, TURNBULL B, MOUSTAFA N. A blockchain-enabled explainable federated learning for securing Internet-of-things-based social media 3.0 networks[J]. IEEE Transactions on Computational Social Systems, 2024, 11(4): 4681-4697.
[34] WANG N Y, YANG W T, WANG X D, et al. A blockchain based privacy-preserving federated learning scheme for Internet of Vehicles[J]. Digital Communications and Networks, 2024, 10(1): 126-134.
[35] MIAO Y B, LIU Z T, LI H W, et al. Privacy-preserving Byzantine-robust federated learning via blockchain systems[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 2848-2861.
[36] SUN Z, WAN J P, YIN L H, et al. A blockchain-based audit approach for encrypted data in federated learning[J]. Digital Communications and Networks, 2022, 8(5): 614-624.
[37] LIU J W, HE X Y, SUN R, et al. Privacy-preserving data sharing scheme with FL via MPC in financial permissioned blockchain[C]//Proceedings of the IEEE International Conference on Communications. Piscataway: IEEE, 2021: 1-6.
[38] XIONG R T, REN W, ZHAO S H, et al. CoPiFL: a collusion-resistant and privacy-preserving federated learning crowdsourcing scheme using blockchain and homomorphic encry-ption[J]. Future Generation Computer Systems, 2024, 156: 95-104.
[39] HIJAZI N M, ALOQAILY M, GUIZANI M, et al. Secure federated learning with fully homomorphic encryption for IoT communications[J]. IEEE Internet of Things Journal, 2024, 11(3): 4289-4300.
[40] YANG R Z, ZHAO T H, YU F R, et al. Blockchain-based federated learning with enhanced privacy and security using homomorphic encryption and reputation[J]. IEEE Internet of Things Journal, 2024, 11(12): 21674-21688.
[41] AHMAD JALALI N, CHEN H S. Comprehensive framework for implementing blockchain-enabled federated learning and full homomorphic encryption for chatbot security system[J]. Cluster Computing, 2024, 27(8): 10859-10882.
[42] KESHAVARZKALHORI G, PéREZ-SOLà C, NAVARRO-ARRIBAS G, et al. Federify: a verifiable federated learning scheme based on zkSNARKs and blockchain[J]. IEEE Access, 2023, 12: 3240-3255.
[43] HU S L, LI J F, ZHANG C X, et al. The blockchain-based edge computing framework for privacy-preserving federated learning[C]//Proceedings of the 2021 IEEE International Conference on Blockchain. Piscataway: IEEE, 2021: 566-571.
[44] GUPTA B B, GAURAV A, ARYA V. Secure and privacy-preserving decentralized federated learning for personalized recommendations in consumer electronics using blockchain and homomorphic encryption[J]. IEEE Transactions on Consumer Electronics, 2024, 70(1): 2546-2556.
[45] HEISS J, GRüNEWALD E, TAI S, et al. Advancing blockchain-based federated learning through verifiable off-chain computations[C]//Proceedings of the 2022 IEEE International Conference on Blockchain. Piscataway: IEEE, 2022: 194-201.
[46] SHOKRI R, SHMATIKOV V. Privacy-preserving deep learning[C]//Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security. New York: ACM, 2015: 1310-1321.
[47] HITAJ B, ATENIESE G, PEREZ-CRUZ F. Deep models under the GAN: information leakage from collaborative deep learning[C]//Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. New York: ACM, 2017: 603-618.
[48] MUGUNTHAN V, RAHMAN R, KAGAL L J A P A. BlockFlow: an accountable and privacy-preserving solution for federated learning[J]. arXiv:2007.03856, 2020.
[49] JIA B, ZHANG X S, LIU J W, et al. Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT[J]. IEEE Transactions on Industrial Informatics, 2022, 18(6): 4049-4058.
[50] WU X, WANG Z, ZHAO J, et al. FedBC: blockchain-based decentralized federated learning[C]//Proceedings of the 2020 IEEE International Conference on Artificial Intelligence and Computer Applications. Piscataway: IEEE, 2020: 217-221.
[51] PHONG L T, AONO Y, HAYASHI T, et al. Privacy-preserving deep learning via additively homomorphic encryption[J]. IEEE Transactions on Information Forensics and Security, 2018, 13(5): 1333-1345.
[52] 张世文, 陈双, 梁伟, 等. 联邦学习中的攻击手段与防御机制研究综述[J]. 计算机工程与应用, 2024, 60(5): 1-16.
ZHANG S W, CHEN S, LIANG W, et al. Survey on attack methods and defense mechanisms in federated learning[J]. Computer Engineering and Applications, 2024, 60(5): 1-16.
[53] DESAI H B, OZDAYI M S, KANTARCIOGLU M. Block-FLA: accountable federated learning via hybrid blockchain architecture[C]//Proceedings of the Eleventh ACM Conference on Data and Application Security and Privacy. New York: ACM, 2021: 101-112.
[54] ABOU EL HOUDA Z, HAFID A S, KHOUKHI L. MiTFed: a privacy preserving collaborative network attack mitigation framework based on federated learning using SDN and blockchain[J]. IEEE Transactions on Network Science and Engineering, 2023, 10(4): 1985-2001.
[55] GUO J, LIU Z, LAM K Y, et al. Secure weighted aggreg-ation for federated learning[J]. arXiv:2010.08730, 2020.
[56] GHOSH A, HONG J, YIN D, et al. Robust federated learning in a heterogeneous environment[J]. arXiv:1906.06629, 2019.
[57] BLANCHARD P, EL MHAMDI E M, GUERRAOUI R, et al. Machine learning with adversaries: Byzantine tolerant gradient descent[C]//Advances in Neural Information Proces-sing Systems, 2017: 119-129.
[58] DAMASKINOS G, EL-MHAMDI E M, GUERRAOUI R, et al. Aggregathor: Byzantine machine learning via robust gradient aggregation[C]//Proceedings of the Second Conference on Machine Learning and Systems, 2019: 81-106.
[59] LI T, SAHU A K, ZAHEER M, et al. Federated optimiz-ation in heterogeneous networks[C]//Proceedings of the Third Conference on Machine Learning and Systems, 2020: 429-450.
[60] WANG H Y, YUROCHKIN M, SUN Y K, et al. Federated learning with matched averaging[J]. arXiv:2002.06440, 2020.
[61] EK S, PORTET F, LALANDA P, et al. A federated learning aggregation algorithm for pervasive computing: evaluation and comparison[C]//Proceedings of the 2021 IEEE International Conference on Pervasive Computing and Communications. Piscataway: IEEE, 2021: 1-10.
[62] GUENDOUZI S B, OUCHANI S, MALKI M. Enhancing the aggregation of the federated learning for the industrial cyber physical systems[C]//Proceedings of the 2022 IEEE International Conference on Cyber Security and Resilience. Piscataway: IEEE, 2022: 197-202.
[63] YE R, NI Z Y, XU C X, et al. FedFM: anchor-based feature matching for data heterogeneity in federated learning[J]. IEEE Transactions on Signal Processing, 2023, 71: 4224-4239.
[64] PALIHAWADANA C, WIRATUNGA N, WIJEKOON A, et al. FedSim: similarity guided model aggregation for federated learning[J]. Neurocomputing, 2022, 483: 432-445.
[65] MCMAHAN H B, MOORE E, RAMAGE D, et al. Federated learning of deep networks using model averaging[J]. arXiv:1602.05629, 2016.
[66] GHUHAN A M, VINAY A, KUMAR S A, et al. Federated learning with personalization layers[J]. arXiv:1912.00818, 2019.
[67] KASYAP H, TRIPATHY S. Privacy-preserving and Byzantine-robust federated learning framework using permissioned blockchain[J]. Expert Systems with Applications, 2024, 238: 122210.
[68] CHEN F, LUO M, DONG Z, et al. Federated meta-learning with fast convergence and efficient communication[J]. arXiv:1802.07876, 2018.
[69] PENG Z, XU J L, CHU X W, et al. VFChain: enabling verifiable and auditable federated learning via blockchain systems[J]. IEEE Transactions on Network Science and Engineering, 2022, 9(1): 173-186.
[70] ZHOU M, YANG Z, YU H Y, et al. VDFChain: secure and verifiable decentralized federated learning via committee-based blockchain[J]. Journal of Network and Computer Applic-ations, 2024, 223: 103814.
[71] TOYODA K, ZHANG A N. Mechanism design for an incentive-aware blockchain-enabled federated learning platform[C]//Proceedings of the 2019 IEEE International Conference on Big Data. Piscataway: IEEE, 2019: 395-403.
[72] MARTINEZ I, FRANCIS S, HAFID A S. Record and reward federated learning contributions with blockchain[C]//Proceedings of the 2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery. Piscataway: IEEE, 2019: 50-57.
[73] UR REHMAN M H, SALAH K, DAMIANI E, et al. Towards blockchain-based reputation-aware federated learning[C]//Proceedings of the 39th IEEE Conference on Computer Communications, INFOCOM Workshops. Piscataway: IEEE, 2020: 183-188.
[74] BARANWAL SOMY N, KANNAN K, ARYA V, et al. Ownership preserving AI market places using blockchain[C]//Proceedings of the 2019 IEEE International Conference on Blockchain. Piscataway: IEEE, 2019: 156-165.
[75] WANG X F, ZHAO Y F, QIU C, et al. InFEDge: a blockchain-based incentive mechanism in hierarchical federated learning for end-edge-cloud communications[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(12): 3325-3342.
[76] 周茂君, 潘宁. 赋权与重构: 区块链技术对数据孤岛的破解[J]. 新闻与传播评论, 2018, 71(5): 58-67.
ZHOU M J, PAN N. Empowerment and reconstruction: blockchain technology breaks data isolated island[J]. Journalism & Communication Review, 2018, 71(5): 58-67.
[77] 谭荣杰, 洪智勇, 余文华, 等. 非独立同分布数据下的去中心化联邦学习策略[J]. 计算机工程与应用, 2023, 59(1): 269-277.
TAN R J, HONG Z Y, YU W H, et al. Decentralized federated learning strategy for non-independent and identically distributed data[J]. Computer Engineering and Applications, 2023, 59(1): 269-277.
[78] HUANG G J, WU Q, LI J Y, et al. IMFL-AIGC: incentive mechanism design for federated learning empowered by artificial intelligence generated content[J]. IEEE Transactions on Mobile Computing, 2024, 23(12): 12603-12620.
[79] TANG C B, YANG B S, XIE X D, et al. An incentive mechanism for federated learning: a continuous zero-determinant strategy approach[J]. IEEE/CAA Journal of Automatica Sinica, 2024, 11(1): 88-102.
[80] XUAN S C, WANG M D, ZHANG J Y, et al. An incentive mechanism design for federated learning with multiple task publishers by contract theory approach[J]. Information Sciences, 2024, 664: 120330.