Membership Information Leakage in Federated Contrastive Learning

arXiv:2404.16850v1 Announce Type: new
Abstract: Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data, which can serve as a versatile feature extractor for diverse downstream tasks. Nonetheless, FCL is susceptible to privacy risks, such as membership information leakage, stemming from its distributed nature, an aspect often overlooked in current solutions. This study delves into the feasibility of executing …

arxiv can clients cs.cr data data privacy decentralized feature federated global information information leakage privacy