Decentralized Federated Learning Algorithm Under Adversary Eavesdropping

• Published in: IEEE/CAA journal of automatica sinica Vol. 12; no. 2; pp. 448 - 456
• Main Authors: Xu, Lei, Xu, Danya, Yi, Xinlei, Deng, Chao, Chai, Tianyou, Yang, Tao
• Format: Journal Article
• Language: English
• Published: Piscataway Chinese Association of Automation (CAA) 01.02.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adversary eavesdropping; Algorithms; Classification algorithms; Communication channels; Data privacy; Datasets; decentralized federated learning; Eavesdropping; Fault diagnosis; Federated learning; Image classification; Machine learning; Parameters; Privacy; privacy protection; Protection; stochastic gradient descent; Stochastic processes; Training
• ISSN: 2329-9266; 2329-9274
• DOI: 10.1109/JAS.2024.125079

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.