Decentralized Federated Learning Algorithm Under Adversary Eavesdropping
IEEE/CAA Journal of Automatica Sinica · 2025-02 · 12 (2) · 448-456
DOI: 10.1109/jas.2024.125079 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE/CAA Journal of Automatica Sinica, 2025-02. Verfasst von Lei Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
In this paper, we study the decentralized federated learning problem, which involves the collaborative training of a global model among multiple devices while ensuring data privacy. In classical federated learning, the communication channel between the devices poses a potential risk of compromising private information. To reduce the risk of adversary eavesdropping in the communication channel, we propose TRADE (transmit difference weight) concept. This concept replaces the decentralized federated learning algorithm's transmitted weight parameters with differential weight parameters, enhancing the privacy data against eavesdropping. Subsequently, by integrating the TRADE concept with the primal-dual stochastic gradient descent (SGD) algorithm, we propose a decentralized TRADE primal-dual SGD algorithm. We demonstrate that our proposed algorithm's convergence properties are the same as those of the primal-dual SGD algorithm while providing enhanced privacy protection. We validate the algorithm's performance on fault diagnosis task using the Case Western Reserve University dataset, and image classification tasks using the CIFAR-10 and CIFAR-100 datasets, revealing model accuracy comparable to centralized federated learning. Additionally, the experiments confirm the algorithm's privacy protection capability.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Xu, L., Xu, D., Yi, X., Deng, C., Chai, T., & Yang, T. (2025). Decentralized Federated Learning Algorithm Under Adversary Eavesdropping. IEEE/CAA Journal of Automatica Sinica, 12(2), 448-456. https://doi.org/10.1109/jas.2024.125079
Vancouver
Xu L, Xu D, Yi X, Deng C, Chai T, Yang T. Decentralized Federated Learning Algorithm Under Adversary Eavesdropping. IEEE/CAA Journal of Automatica Sinica. 2025;12(2):448-456. doi:10.1109/jas.2024.125079
BibTeX
@article{Xu2025,
author = {Xu, Lei and Xu, Danya and Yi, Xinlei and Deng, Chao and Chai, Tianyou and Yang, Tao},
title = {Decentralized Federated Learning Algorithm Under Adversary Eavesdropping},
journal = {IEEE/CAA Journal of Automatica Sinica},
year = {2025},
volume = {12},
number = {2},
pages = {448--456},
doi = {10.1109/jas.2024.125079}
}
EUVIMED