Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels
IEEE Transactions on Wireless Communications · 2024-08 · 23 (8) · 8232-8247
DOI: 10.1109/twc.2023.3347697 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2024-08. Verfasst von Hang Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: General Research Fund through the Research Grants Council of Hong Kong, Area of Excellence Scheme through the Research Grants Council of Hong Kong, NSFC/RGC Collaborative Research Scheme through the Research Grants Council of Hong Kong.
Abstract (Originalsprache)
Federated learning (FL) enables edge devices to collaboratively train machine learning models, with model communication replacing direct data uploading. While over-the-air model aggregation improves communication efficiency, uploading models to an edge server over wireless networks can pose privacy risks. Differential privacy (DP) is a widely used quantitative technique to measure statistical data privacy in FL. Previous research has focused on over-the-air FL with a single-antenna server, leveraging communication noise to enhance user-level DP. This approach achieves the so-called “free DP” by controlling transmit power rather than introducing additional DP-preserving mechanisms at devices, such as adding artificial noise. In this paper, we study differentially private over-the-air FL over a multiple-input multiple-output (MIMO) fading channel. We show that FL model communication with a multiple-antenna server amplifies privacy leakage when the multiple-antenna server employs separate receive combining for model aggregation and information inference. Consequently, relying solely on communication noise, as done in the multiple-input single-output system, cannot meet high privacy requirements, and a device-side privacy-preserving mechanism is necessary for optimal DP design. We analyze the learning convergence and privacy loss of the studied FL system and propose a transceiver design algorithm based on alternating optimization. Numerical results demonstrate that the proposed method achieves a better privacy-learning trade-off compared to prior work.
Förderung
- General Research Fund through the Research Grants Council of Hong Kong
- Area of Excellence Scheme through the Research Grants Council of Hong Kong
- NSFC/RGC Collaborative Research Scheme through the Research Grants Council of Hong Kong
- Guangzhou Municipal Science and Technology Project
Zitieren
APA
Liu, H., Yan, J., & Zhang, Y. A. (2024). Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels. IEEE Transactions on Wireless Communications, 23(8), 8232-8247. https://doi.org/10.1109/twc.2023.3347697
Vancouver
Liu H, Yan J, Zhang YA. Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels. IEEE Transactions on Wireless Communications. 2024;23(8):8232-8247. doi:10.1109/twc.2023.3347697
BibTeX
@article{Liu2024,
author = {Liu, Hang and Yan, Jia and Zhang, Ying-Jun Angela},
title = {Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels},
journal = {IEEE Transactions on Wireless Communications},
year = {2024},
volume = {23},
number = {8},
pages = {8232--8247},
doi = {10.1109/twc.2023.3347697}
}
EUVIMED