Advancing Blockchain-based Federated Learning through Verifiable Off-chain Computations

被引:11
|
作者
Heiss, Jonathan [1 ]
Grunewald, Elias [1 ]
Tai, Stefan [1 ]
Haimerl, Nikolas [2 ]
Schulte, Stefan [3 ]
机构
[1] TU Berlin, Informat Syst Engn, Berlin, Germany
[2] TU Wien, Distributed Syst Grp, Vienna, Austria
[3] TU Hamburg, Christian Doppler Lab Blockchain Technol Internet, Hamburg, Germany
关键词
federated learning; blockchain; off-chain computations; verifiability; zero-knowledge proofs; zokrates; FRAMEWORK;
D O I
10.1109/Blockchain55522.2022.00034
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Federated learning may be subject to both global aggregation attacks and distributed poisoning attacks. Blockchain technology along with incentive and penalty mechanisms have been suggested to counter these. In this paper, we explore verifiable off-chain computations using zero-knowledge proofs as an alternative to incentive and penalty mechanisms in blockchain-based federated learning. In our solution, learning nodes, in addition to their computational duties, act as off-chain provers submitting proofs to attest computational correctness of parameters that can be verified on the blockchain. We demonstrate and evaluate our solution through a health monitoring use case and proof-of-concept implementation leveraging the ZoKrates language and tools for smart contract-based on-chain model management. Our research introduces verifiability of correctness of learning processes, thus advancing blockchain-based federated learning.
引用
收藏
页码:194 / 201
页数:8
相关论文
共 50 条
  • [1] Advancing Federated Learning through Verifiable Computations and Homomorphic Encryption
    Zhang, Bingxue
    Lu, Guangguang
    Qiu, Pengpeng
    Gui, Xumin
    Shi, Yang
    [J]. ENTROPY, 2023, 25 (11)
  • [2] Compact Learning Model for Dynamic Off-Chain Routing in Blockchain-Based IoT
    Li, Zhenni
    Su, Wensheng
    Xu, Minrui
    Yu, Rong
    Niyato, Dusit
    Xie, Shengli
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2022, 40 (12) : 3615 - 3630
  • [3] A verifiable and privacy-preserving blockchain-based federated learning approach
    Ullah, Irshad
    Deng, Xiaoheng
    Pei, Xinjun
    Jiang, Ping
    Mushtaq, Husnain
    [J]. PEER-TO-PEER NETWORKING AND APPLICATIONS, 2023, 16 (05) : 2256 - 2270
  • [4] A verifiable and privacy-preserving blockchain-based federated learning approach
    Irshad Ullah
    Xiaoheng Deng
    Xinjun Pei
    Ping Jiang
    Husnain Mushtaq
    [J]. Peer-to-Peer Networking and Applications, 2023, 16 : 2256 - 2270
  • [5] TrustDFL: A Blockchain-Based Verifiable and Trusty Decentralized Federated Learning Framework
    Yang, Jinsheng
    Zhang, Wenfeng
    Guo, Zhaohui
    Gao, Zhen
    [J]. ELECTRONICS, 2024, 13 (01)
  • [6] Blockchain-based Off-chain Extension Model for Geographic Information Data
    Zhao, Jie
    Liu, Wenfen
    Wang, Jing
    Li, Song
    Lu, Yongcan
    [J]. PROCEEDINGS OF 2023 7TH INTERNATIONAL CONFERENCE ON ELECTRONIC INFORMATION TECHNOLOGY AND COMPUTER ENGINEERING, EITCE 2023, 2023, : 1036 - 1041
  • [7] Secure verifiable aggregation for blockchain-based federated averaging
    Zhu, Saide
    Li, Ruinian
    Cai, Zhipeng
    Kim, Donghyun
    Seo, Daehee
    Li, Wei
    [J]. HIGH-CONFIDENCE COMPUTING, 2022, 2 (01):
  • [8] Blockchain-Based Practical and Privacy-Preserving Federated Learning with Verifiable Fairness
    Zhang, Yitian
    Tang, Yuming
    Zhang, Zijian
    Li, Meng
    Li, Zhen
    Khan, Salabat
    Chen, Huaping
    Cheng, Guoqiang
    [J]. MATHEMATICS, 2023, 11 (05)
  • [9] Secure Access Control to Data in Off-Chain Storage in Blockchain-Based Consent Systems
    Goint, Mongetro
    Bertelle, Cyrille
    Duvallet, Claude
    [J]. MATHEMATICS, 2023, 11 (07)
  • [10] A Blockchain-Based Product Traceability System with Off-Chain EPCIS and IoT Device Authentication
    Li, Lulu
    Qu, Huan
    Wang, Huaizhen
    Wang, Junyu
    Wang, Bozhi
    Wang, Wei
    Xu, Jinfei
    Wang, Zhihui
    [J]. SENSORS, 2022, 22 (22)