United We Defend: Collaborative Membership Inference Defenses in Federated Learning

Li Bai, The Hong Kong Polytechnic University; Junxu Liu, The Hong Kong Polytechnic University and PolyU Research Centre for Privacy and Security Technologies in Future Smart Systems; Sen Zhang, Xinwei Zhang, and Qingqing Ye, The Hong Kong Polytechnic University; Haibo Hu, The Hong Kong Polytechnic University and PolyU Research Centre for Privacy and Security Technologies in Future Smart Systems

Membership inference attacks (MIAs), which determine whether a specific data point was included in the training set of a target model, have posed severe threats in federated learning (FL). Unfortunately, existing MIA defenses, typically applied independently to each client in FL, are ineffective against powerful trajectory-based MIAs that exploit temporal information throughout the training process to infer membership status. In this paper, we investigate a new FL defense scenario driven by heterogeneous privacy needs and privacy-utility trade-offs, where only a subset of clients are defended, as well as a collaborative defense mode where clients cooperate to mitigate membership privacy leakage. To this end, we introduce CoFedMID, a collaborative defense framework against MIAs in FL, which limits local model memorization of training samples and, through a defender coalition, enhances privacy protection and model utility. Specifically, CoFedMID consists of three modules: a class-guided partition module for selective local training samples, a utility-aware compensation module to recycle contributive samples and prevent their overconfidence, and an aggregation-neutral perturbation module that injects noise for cancellation at the coalition level into client updates. Extensive experiments on three datasets show that our defense framework significantly reduces the performance of seven MIAs while incurring only a small utility loss. These results are consistently verified across various defense settings.

USENIX Security '26 Open Access Sponsored by
King Abdullah University of Science and Technology (KAUST)

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {317845,
author = {Li Bai and Junxu Liu and Sen Zhang and Xinwei Zhang and Qingqing Ye and Haibo Hu},
title = {United We Defend: Collaborative Membership Inference Defenses in Federated Learning},
booktitle = {35th USENIX Security Symposium (USENIX Security 26)},
year = {2026},
isbn = {978-1-939133-58-8},
address = {Baltimore, MD},
pages = {1967--1986},
url = {https://www.usenix.org/conference/usenixsecurity26/presentation/bai},
publisher = {USENIX Association},
month = aug
}

Presentation Video