App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 7

Model-secure and robust aggregation algorithms for federated learning

Wang Bin1,2,3,4
Chen Yun1,2,3
Zhang Lei1,2,3
Chen Jie1,2,3
Zheng Bing1,2,3
1. School of Information and Electronic Technology, Jiamusi University, Jiamusi Heilongjiang 154007, China
2. Heilongjiang Province Key Laboratory of Autonomous Intelligence and Information Processing, School of Information and Electronic Technology, Jiamusi University, Jiamusi Heilongjiang 154007, China
3. Jiamusi Key Laboratory of Satellite Navigation Technology and Equipment Engineering Technology, School of Information and Electronic Technology, Jiamusi University, Jiamusi Heilongjiang 154007, China
4. Dept. of Science and Technology, Jiamusi University 154007, Heilongjiang, China
DOI: 10.19734/j.issn.1001-3695.2025.09.0442

Abstract

To address the threats of gradient poisoning attacks and privacy leakage risks in federated learning, this paper proposes a secure and robust gradient aggregation algorithm named MSRAFL (Model-Secure and Robust Aggregation Algorithms for Federated Learning) . The algorithm effectively defends against gradient poisoning attacks launched by malicious clients while preserving client data privacy, thereby enhancing the robustness and security of the global model. First, MSRAFL incorporates a differential privacy mechanism by applying gradient clipping and injecting Gaussian noise to ensure privacy protection. Second, it designs a guidance direction based on historical gradients and combines cosine similarity with a dynamic trust threshold to constrain gradient projections, thereby correcting deviations in the update direction caused by noise and attacks. Furthermore, it evaluates client credibility based on changes in model loss and dynamically assigns aggregation weights using cosine similarity to suppress the impact of malicious gradients. Experimental results on real-world datasets demonstrate that even with 30% of poisoned models, MSRAFL maintains model accuracy at around 0.8, outperforming existing aggregation algorithms. This indicates that MSRAFL effectively enhances the defense capability of federated learning systems against poisoning attacks under strict privacy protection, achieving both privacy security and model robustness.

Foundation Support

黑龙江省高等学校基本科研业务费优秀创新团队建设项目(2023-KYYWF-0639)
佳木斯大学国家基金培育项目(JMSUGPZR2022-014)
黑龙江省省属本科高校优秀青年教师基础研究支持计划(YQJH2024239)
黑龙江省自然科学基金联合基金培育项目(PL2024F002)
佳木斯大学博士专项科研基金启动项目(JMSUBZ2022-12)
黑龙江省教育厅创新团队项目(2024-KYYWF-0611)
佳木斯大学"东极"学术团队项目(DJXSTD202413)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.09.0442
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 7

Publish History

[2026-03-13] Accepted Paper

Cite This Article

王斌, 陈运, 张磊, 等. 联邦学习的梯度安全鲁棒聚合算法 [J]. 计算机应用研究, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0442. (Wang Bin, Chen Yun, Zhang Lei, et al. Model-secure and robust aggregation algorithms for federated learning [J]. Application Research of Computers, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0442. )

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)