Robust federated contrastive recommender system against targeted model poisoning attack
Science China Information Sciences · 2025-04 · 68 (4)
DOI: 10.1007/s11432-024-4272-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Science China Information Sciences, online erschienen am 18.03.2025. Verfasst von Wei Yuan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Federated recommender systems (FedRecs) have garnered increasing attention recently, thanks to their privacy-preserving benefits. However, the decentralized and open characteristics of current FedRecs present at least two dilemmas. First, the performance of FedRecs is compromised due to highly sparse on-device data for each client. Second, the system’s robustness is undermined by the vulnerability to model poisoning attacks launched by malicious users. In this paper, we introduce a novel contrastive learning framework designed to fully leverage the client’s sparse data through embedding augmentation, referred to as CL4FedRec. Unlike previous contrastive learning approaches in FedRecs that necessitate clients to share their private parameters, our CL4FedRec aligns with the basic FedRec learning protocol, ensuring compatibility with most existing FedRec implementations. We then evaluate the robustness of FedRecs equipped with CL4FedRec by subjecting it to several state-of-the-art model poisoning attacks. Surprisingly, our observations reveal that contrastive learning tends to exacerbate the vulnerability of FedRecs to these attacks. This is attributed to the enhanced embedding uniformity, making the polluted target item embedding easily proximate to popular items. Based on this insight, we propose an enhanced and robust version of CL4FedRec (rCL4FedRec) by introducing a regularizer to maintain the distance among item embeddings with different popularity levels. Extensive experiments conducted on four commonly used recommendation datasets demonstrate that rCL4FedRec significantly enhances both the model’s performance and the robustness of FedRecs.
Zitieren
APA
Yuan, W., Yang, C., Qu, L., Ye, G., Nguyen, Q. V. H., & Yin, H. (2025). Robust federated contrastive recommender system against targeted model poisoning attack. Science China Information Sciences, 68(4). https://doi.org/10.1007/s11432-024-4272-y
Vancouver
Yuan W, Yang C, Qu L, Ye G, Nguyen QVH, Yin H. Robust federated contrastive recommender system against targeted model poisoning attack. Science China Information Sciences. 2025;68(4). doi:10.1007/s11432-024-4272-y
BibTeX
@article{Yuan2025,
author = {Yuan, Wei and Yang, Chaoqun and Qu, Liang and Ye, Guanhua and Nguyen, Quoc Viet Hung and Yin, Hongzhi},
title = {Robust federated contrastive recommender system against targeted model poisoning attack},
journal = {Science China Information Sciences},
year = {2025},
volume = {68},
number = {4},
doi = {10.1007/s11432-024-4272-y}
}
EUVIMED