EUVIMEDEUVIMED entdecken
Crossref

A New Federated Learning Framework Against Gradient Inversion Attacks

Pengxin Guo, Shuang Zeng, Wenhao Chen, Xiaodan Zhang, Weihong Ren, Yuyin Zhou, Liangqiong Qu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (16) · 16969-16977

DOI: 10.1609/aaai.v39i16.33865 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Pengxin Guo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively ``breaks the direct connection'' between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL.

Zitieren

APA

Guo, P., Zeng, S., Chen, W., Zhang, X., Ren, W., Zhou, Y., & Qu, L. (2025). A New Federated Learning Framework Against Gradient Inversion Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 39(16), 16969-16977. https://doi.org/10.1609/aaai.v39i16.33865

Vancouver

Guo P, Zeng S, Chen W, Zhang X, Ren W, Zhou Y, et al. A New Federated Learning Framework Against Gradient Inversion Attacks. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(16):16969-16977. doi:10.1609/aaai.v39i16.33865

BibTeX
@article{Guo2025,
  author = {Guo, Pengxin and Zeng, Shuang and Chen, Wenhao and Zhang, Xiaodan and Ren, Weihong and Zhou, Yuyin and Qu, Liangqiong},
  title = {A New Federated Learning Framework Against Gradient Inversion Attacks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {16},
  pages = {16969--16977},
  doi = {10.1609/aaai.v39i16.33865}
}
Kostenlos starten →