CLMIA: Membership Inference Attacks via Unsupervised Contrastive Learning

TL;DR

This paper introduces CLMIA, a novel membership inference attack leveraging unsupervised contrastive learning, which effectively infers membership with minimal labeled data, outperforming existing methods across various datasets and models.

Contribution

The paper presents CLMIA, an unsupervised contrastive learning-based attack that requires only limited labeled data, improving membership inference accuracy in realistic scenarios.

Findings

CLMIA outperforms existing attacks on multiple datasets.

Less labeled identity information enhances attack effectiveness.

Attack performance varies with the proportion of labeled data.

Abstract

Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit this feature to determine whether a data sample is used for training a machine learning model. However, in realistic scenarios, it is difficult for the adversary to obtain enough qualified samples that mark accurate identity information, especially since most samples are non-members in real world applications. To address this limitation, in this paper, we propose a new attack method called CLMIA, which uses unsupervised contrastive learning to train an attack model without using extra membership status information. Meanwhile, in CLMIA, we require only a small amount of data with known membership status to fine-tune the attack model. Experimental results demonstrate that CLMIA performs better than existing attack methods for different datasets and model structures, especially with data with less marked identity information. In addition, we experimentally find that the attack performs differently for different proportions of labeled identity information for member and non-member data. More analysis proves that our attack method performs better with less labeled identity information, which applies to more realistic scenarios.