EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unveiling Privacy Risks in Federated Learning: An Efficient Bias-Based Membership Inference Attack and Adaptive Defense

Liwei Zhang, Xingwu Wang, Linghui Li, Ruobin Dou, Xiaoyong Li

Future Internet · 19.11.2026 · 18 (11) · 640

DOI: 10.3390/fi18110640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 19.11.2026. Verfasst von Liwei Zhang und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning provides a privacy-enhancing paradigm for distributed collaborative learning across diverse application scenarios, yet it inherently contains vulnerabilities that can lead to information leakage. As critical parameters in deep neural networks, biases play a decisive role in shaping decision boundaries. In this paper, we reveal that these biases introduce susceptibility within federated learning, making it vulnerable to membership inference attacks. Specifically, we examine two distinct manifestations of bias-based membership inference attacks (BMIA), distinguished by the roles in federated learning: a local attack launched by individual participants, and a global attack initiated by the central server. For both scenarios, we develop efficient BMIA strategies. We employ a shallow neural network to identify whether a given data point is part of the training dataset, and a straightforward difference-comparison mechanism to identify the specific participant’s dataset from which the data is derived. Furthermore, we introduce a novel adaptive noise pruning defense (ANPD) mechanism designed to effectively mitigate BMIA without substantially degrading the performance of the target model. Comprehensive experiments conducted on four public datasets covering location services, retail, healthcare, and image recognition demonstrate the superiority of our attacks, which achieve higher accuracy than state-of-the-art methods and are robust against prevalent defenses. Additionally, the experiments demonstrate that our proposed defense strategy significantly counteracts the proposed BMIA and other prevalent attack techniques.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, L., Wang, X., Li, L., Dou, R., & Li, X. (2026). Unveiling Privacy Risks in Federated Learning: An Efficient Bias-Based Membership Inference Attack and Adaptive Defense. Future Internet, 18(11), 640. https://doi.org/10.3390/fi18110640

Vancouver

Zhang L, Wang X, Li L, Dou R, Li X. Unveiling Privacy Risks in Federated Learning: An Efficient Bias-Based Membership Inference Attack and Adaptive Defense. Future Internet. 2026;18(11):640. doi:10.3390/fi18110640

BibTeX
@article{Zhang2026,
  author = {Zhang, Liwei and Wang, Xingwu and Li, Linghui and Dou, Ruobin and Li, Xiaoyong},
  title = {Unveiling Privacy Risks in Federated Learning: An Efficient Bias-Based Membership Inference Attack and Adaptive Defense},
  journal = {Future Internet},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {640},
  doi = {10.3390/fi18110640}
}
Kostenlos starten →