Membership Information Leakage in Federated Contrastive Learning

TL;DR

This paper investigates privacy risks in Federated Contrastive Learning by demonstrating effective membership inference attacks, revealing potential privacy breaches in decentralized, unlabeled data learning frameworks.

Contribution

It introduces two novel membership inference attacks specific to FCL, highlighting vulnerabilities and the need for privacy-preserving mechanisms in federated contrastive learning.

Findings

Attacks successfully infer membership with high accuracy

Privacy risks are significant in federated contrastive learning

Experimental results validate attack effectiveness across datasets

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 a membership inference attack on FCL and proposes a robust attack methodology. The attacker's objective is to determine if the data signifies training member data by accessing the model's inference output. Specifically, we concentrate on attackers situated within a client framework, lacking the capability to manipulate server-side aggregation methods or discern the training status of other clients. We introduce two membership inference attacks tailored for FCL: the \textit{passive membership inference attack} and the \textit{active membership inference attack}, contingent on the attacker's involvement in local model training. Experimental findings across diverse datasets validate the effectiveness of our attacks and underscore the inherent privacy risks associated with the federated contrastive learning paradigm.