About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Wireless Internet. 15th EAI International Conference, WiCON 2022, Virtual Event, November 2022, Proceedings

Research Article

Decentralized Federated Learning: A Defense Against Gradient Inversion Attack

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-27041-3_4,
        author={Guangxi Lu and Zuobin Xiong and Ruinian Li and Wei Li},
        title={Decentralized Federated Learning: A Defense Against Gradient Inversion Attack},
        proceedings={Wireless Internet. 15th EAI International Conference, WiCON 2022, Virtual Event, November 2022, Proceedings},
        proceedings_a={WICON},
        year={2023},
        month={2},
        keywords={Federated learning Peer to peer network Privacy protection},
        doi={10.1007/978-3-031-27041-3_4}
    }
    
  • Guangxi Lu
    Zuobin Xiong
    Ruinian Li
    Wei Li
    Year: 2023
    Decentralized Federated Learning: A Defense Against Gradient Inversion Attack
    WICON
    Springer
    DOI: 10.1007/978-3-031-27041-3_4
Guangxi Lu1, Zuobin Xiong1, Ruinian Li2, Wei Li1,*
  • 1: Department of Computer Science, Georgia State University
  • 2: Department of Computer Science, Bowling Green State University
*Contact email: wli28@gsu.edu

Abstract

Federated learning (FL) is a machine learning technique that enables data to be stored and calculated on geographically distributed local clients. In centralized FL, there is an orchestrating system server responsible for aggregating local client parameters. Such a design is vulnerable to gradient inversion attacks where a malicious central server can restore the client’s data through the model gradients. This paper proposes a Decentralized Federated Learning (DFL) method to mitigate the gradient inversion attack. We design a federated learning framework in a decentralized structure, where only peer-to-peer communication is adopted to transfer model parameters for aggregating and updating local models. Extensive experiments and detailed case studies are conducted on a real dataset, through which we demonstrate that the proposed DFL mechanism has excellent performance and is resistant to gradient inversion attack.

Keywords
Federated learning Peer to peer network Privacy protection
Published
2023-02-18
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-27041-3_4
Copyright © 2022–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL