EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Providing Differential Privacy for Federated Learning Over Wireless: A Cross-Layer Framework

Jiayu Mao, Tongxin Yin, Aylin Yener, Mingyan Liu

IEEE Open Journal of Vehicular Technology · 2026 · 7 · 1049-1065

DOI: 10.1109/ojvt.2026.3672638 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of Vehicular Technology, 2026. Verfasst von Jiayu Mao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) is a distributed machine learning framework that inherently allows edge devices to maintain their local training data, thus providing some level of privacy. However, FL’s model updates still pose a risk of privacy leakage, which must be mitigated. Over-the-air FL (OTA-FL) is an adapted FL design for wireless edge networks that leverages the natural superposition property of the wireless medium. We propose a wireless physical layer (PHY) design for OTA-FL which improves differential privacy (DP) through a fully decentralized, dynamic power control strategy that utilizes both inherent Gaussian noise in the wireless channel and a cooperative jammer (CJ) for additional artificial noise generation when higher privacy levels are required. Although primarily implemented within the Upcycled-FL framework, where a resource-efficient method with first-order approximations is used at every even iteration to decrease the required information from clients, our power control strategy is applicable to any FL framework, including FedAvg and FedProx as shown in the paper. This adaptation showcases the flexibility and effectiveness of our design across different learning algorithms while maintaining a strong emphasis on privacy. Our design removes the need for client-side artificial noise injection for DP, improving client transmission efficiency by shifting the privacy-inducing perturbation to a cooperative jammer, which introduces additional system-level energy consumption. Privacy analysis is provided using the Moments Accountant method. We perform a convergence analysis for non-convex objectives to tackle heterogeneous data distributions, highlighting the inherent trade-offs between privacy and accuracy. Numerical results confirm that our approach with different FL algorithms outperforms the state-of-the-art under the same DP conditions on the non-i.i.d. dataset FEMNIST. The results also demonstrate the effectiveness of cooperative jammer in meeting stringent privacy demands. We further extend to imperfect CSI scenarios and show that adaptive power control combined with Upcycled-FL remains robust under channel estimation errors.

Förderung

  • National Science Foundation

Zitieren

APA

Mao, J., Yin, T., Yener, A., & Liu, M. (2026). Providing Differential Privacy for Federated Learning Over Wireless: A Cross-Layer Framework. IEEE Open Journal of Vehicular Technology, 7, 1049-1065. https://doi.org/10.1109/ojvt.2026.3672638

Vancouver

Mao J, Yin T, Yener A, Liu M. Providing Differential Privacy for Federated Learning Over Wireless: A Cross-Layer Framework. IEEE Open Journal of Vehicular Technology. 2026;7:1049-1065. doi:10.1109/ojvt.2026.3672638

BibTeX
@article{Mao2026,
  author = {Mao, Jiayu and Yin, Tongxin and Yener, Aylin and Liu, Mingyan},
  title = {Providing Differential Privacy for Federated Learning Over Wireless: A Cross-Layer Framework},
  journal = {IEEE Open Journal of Vehicular Technology},
  year = {2026},
  volume = {7},
  pages = {1049--1065},
  doi = {10.1109/ojvt.2026.3672638}
}
Kostenlos starten →