In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 5

Secure and adaptive federated learning framework for Heterogeneous data

Li Gonglia,b
Liu Fangfanga
Lei Hongzhia
Wang Mengtaoa
a. School of Computer & Information Engineering, b. Key Laboratory of Artificial Intelligence & Personalized Learning in Education of Henan Province, Henan Normal University, Xinxiang 453007, Henan, China
DOI: 10.19734/j.issn.1001-3695.2024.07.0346

Abstract

Federated Learning (FL) , as a distributed learning paradigm, achieves local training and remote aggregation, which can effectively protect the security of user data. However, it also introduces issues such as inference attacks and poisoning attacks, especially in the data heterogeneous scenario, poison detection becomes more difficult. To solve the above problems, this paper proposes a secure and adaptive federated learning scheme (SAFL) in the data heterogeneous scenario. Firstly, SAFL designs a cluster-layered privacy protection FL architecture based on the similarity between edge nodes, and proposes a lightweight FL security summing protocol based on zero sharing to protect the privacy of model parameters and prevent collusion between edge nodes and servers. Then, it constructs a ciphertext-based poisoning detection scheme and adaptively adjusts to determine the intra-cluster aggregation coefficients based on detection results to improve model robustness. Secondly, it proposes an adaptive inter-cluster aggregation scheme based on Wasserstein distance to enhance the accuracy of the global model. Finally, we perform a security analysis of SAFL and compare SAFL with existing solutions. Results show that, even with heterogeneous data and blinded model parameters, SAFL can still effectively detect malicious edge nodes, improving model accuracy by approximately 6.2%-45.6%, outperforming existing solutions while maintaining lower computational and communication costs.

Foundation Support

国家自然科学基金项目(62372157)
河南省科技攻关计划项目(232102211057)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.07.0346
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 5

Publish History

[2025-03-06] Accepted Paper

Cite This Article

李功丽, 刘芳芳, 雷宏志, 等. 面向异构数据的安全自适应联邦学习框架 [J]. 计算机应用研究, 2025, 42 (5). (2025-03-06). https://doi.org/10.19734/j.issn.1001-3695.2024.07.0346. (Li Gongli, Liu Fangfang, Lei Hongzhi, et al. Secure and adaptive federated learning framework for Heterogeneous data [J]. Application Research of Computers, 2025, 42 (5). (2025-03-06). https://doi.org/10.19734/j.issn.1001-3695.2024.07.0346. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)