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

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.

Authors

Institutions

Publication Details

Journal
Future Internet
Published
2026-11-19
DOI
https://doi.org/10.3390/fi18110640
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Xingwu Wang, Liwei Zhang, Linghui Li, Ruobin Dou et al.
Future Internet
Privacy-Preserving Technologies in Data
article

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

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

Abstract

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.

Future InternetVol. 18(11)
Beijing University of Posts and Telecommunications (CN), China Mobile (China) (CN), Shaanxi University of Science and Technology (CN)
Privacy-Preserving Technologies in Data
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon