EUVIMEDEUVIMED entdecken
Crossref

MemDefense: Defending Against Membership Inference Attacks in IoT-Based Federated Learning via Pruning Perturbations

Meng Shen, Jin Meng, Ke Xu, Shui Yu, Liehuang Zhu

IEEE Transactions on Big Data · 2025-10 · 11 (5) · 2135-2147

DOI: 10.1109/tbdata.2024.3403388 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Big Data, 2025-10. Verfasst von Meng Shen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Key R&D Program of China, National Defense Basic Scientific Research Program of China, China National Funds for Excellent Young Scientists.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Depending on large-scale devices, the Internet of Things (IoT) provides massive data support for resource sharing and intelligent decision, but privacy risks also increase. As a popular distributed learning framework, Federated Learning (FL) is widely used because it does not need to share raw data while only parameters to collaboratively train models. However, Federated Learning is not spared by some emerging attacks, e.g., membership inference attack. Therefore, for IoT devices with limited resources, it is challenging to design a defense scheme against the membership inference attack ensuring high model utility, strong membership privacy and acceptable time efficiency. In this article, we propose MemDefense, a lightweight defense mechanism to prevent membership inference attack from local models and global models in IoT-based FL, while maintaining high model utility. MemDefense adds crafted pruning perturbations to local models at each round of FL by deploying two key components, i.e., parameter filter and noise generator. Specifically, the parameter filter selects the apposite model parameters which have little impact on the model test accuracy and contribute more to member inference attacks. Then, the noise generator is used to find the pruning noise that can reduce the attack accuracy while keeping high model accuracy, protecting each participant's membership privacy. We comprehensively evaluate MemDefense with different deep learning models and multiple benchmark datasets. The experimental results show that low-cost MemDefense drastically reduces the attack accuracy within limited drop of classification accuracy, meeting the requirements for model utility, membership privacy and time efficiency.

Förderung

  • National Key R&D Program of China
  • National Defense Basic Scientific Research Program of China
  • China National Funds for Excellent Young Scientists
  • NSFC Projects
  • Beijing Nova Program
  • Beijing Natural Science Foundation

Zitieren

APA

Shen, M., Meng, J., Xu, K., Yu, S., & Zhu, L. (2025). MemDefense: Defending Against Membership Inference Attacks in IoT-Based Federated Learning via Pruning Perturbations. IEEE Transactions on Big Data, 11(5), 2135-2147. https://doi.org/10.1109/tbdata.2024.3403388

Vancouver

Shen M, Meng J, Xu K, Yu S, Zhu L. MemDefense: Defending Against Membership Inference Attacks in IoT-Based Federated Learning via Pruning Perturbations. IEEE Transactions on Big Data. 2025;11(5):2135-2147. doi:10.1109/tbdata.2024.3403388

BibTeX
@article{Shen2025,
  author = {Shen, Meng and Meng, Jin and Xu, Ke and Yu, Shui and Zhu, Liehuang},
  title = {MemDefense: Defending Against Membership Inference Attacks in IoT-Based Federated Learning via Pruning Perturbations},
  journal = {IEEE Transactions on Big Data},
  year = {2025},
  volume = {11},
  number = {5},
  pages = {2135--2147},
  doi = {10.1109/tbdata.2024.3403388}
}
Kostenlos starten →