Transparent Contribution Evaluation for Secure Federated Learning on Blockchain

被引:22
|
作者
Ma, Shuaicheng [1 ]
Cao, Yang [2 ]
Xiong, Li [1 ]
机构
[1] Emory Univ, Atlanta, GA 30322 USA
[2] Kyoto Univ, Kyoto, Japan
基金
美国国家卫生研究院; 美国国家科学基金会;
关键词
Blockchain; Federated Learning; Contribution Evaluation; Transparency; Privacy;
D O I
10.1109/ICDEW53142.2021.00023
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Federated Learning is a promising machine learning paradigm when multiple parties collaborate to build a high-quality machine learning model. Nonetheless, these parties are only willing to participate when given enough incentives, such as a fair reward based on their contributions. Many studies explored Shapley value based methods to evaluate each party's contribution to the learned model. However, they commonly assume a semi-trusted server to train the model and evaluate the data owners' model contributions, which lacks transparency and may hinder the success of federated learning in practice. In this work, we propose a blockchain-based federated learning framework and a protocol to transparently evaluate each participant's contribution. Our framework protects all parties' privacy in the model building phase and transparently evaluates contributions based on the model updates. The experiment with the handwritten digits dataset demonstrates that the proposed method can effectively evaluate the contributions.
引用
收藏
页码:88 / 91
页数:4
相关论文
共 50 条
  • [31] Blockchain-Governed Federated Transfer Learning for Secure Internet of Drones Networks
    Wang H.
    Jiang H.
    Wu J.
    Zhou P.
    Huang H.
    IEEE Internet of Things Magazine, 2022, 5 (03): : 134 - 139
  • [32] Blockchain Empowered Asynchronous Federated Learning for Secure Data Sharing in Internet of Vehicles
    Lu, Yunlong
    Huang, Xiaohong
    Zhang, Ke
    Maharjan, Sabita
    Zhang, Yan
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (04) : 4298 - 4311
  • [33] Toward a Secure Healthcare Ecosystem: A Convergence of Edge Analytics, Blockchain, and Federated Learning
    Badidi, Elarbi
    Lamaazi, Hanane
    El Harrouss, Omar
    20TH INTERNATIONAL CONFERENCE ON THE DESIGN OF RELIABLE COMMUNICATION NETWORKS, DRCN 2024, 2024,
  • [34] LSBlocFL: A secure federated learning model combining blockchain and lightweight cryptographic solutions
    Deng, Song
    Zhang, Jie
    Tao, Li
    Jiang, Xindong
    Wang, Feng
    COMPUTERS & ELECTRICAL ENGINEERING, 2023, 111
  • [35] BESIFL: Blockchain-Empowered Secure and Incentive Federated Learning Paradigm in IoT
    Xu, Yajing
    Lu, Zhihui
    Gai, Keke
    Duan, Qiang
    Lin, Junxiong
    Wu, Jie
    Choo, Kim-Kwang Raymond
    IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (08) : 6561 - 6573
  • [36] FREB: Participant Selection in Federated Learning With Reputation Evaluation and Blockchain
    An, Jian
    Tang, Siyu
    Sun, Xiangyan
    Gui, Xiaolin
    He, Xin
    Wang, Feifei
    IEEE TRANSACTIONS ON SERVICES COMPUTING, 2024, 17 (06) : 3685 - 3698
  • [37] Federated Blockchain Learning at the Edge
    Calo, James
    Lo, Benny
    INFORMATION, 2023, 14 (06)
  • [38] Optimized Secure Federated Learning for Event Detection in Big Data using Blockchain Mechanism
    Lakshmi, Prasanna
    Swapnika, K.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2023, 14 (05) : 389 - 395
  • [39] BVFB: TRAINING BEHAVIOR VERIFICATION MECHANISM FOR SECURE BLOCKCHAIN-BASED FEDERATED LEARNING
    Zhang, Zhaohui
    Hu, Jiawei
    Ma, Lina
    Pei, Ruoxuan
    Wang, Pengwei
    COMPUTING AND INFORMATICS, 2022, 41 (06) : 1401 - 1424
  • [40] BSFL: A blockchain-oriented secure federated learning scheme for 5G
    Han, Gang
    Ma, Weiran
    Zhang, Yinghui
    Liu, Yuyuan
    Liu, Shuanggen
    JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2025, 89