Similarity Distribution based Membership Inference Attack on Person Re-identification

TL;DR

This paper introduces a novel membership inference attack on person re-identification models, leveraging the distribution shift in inter-sample similarities, which effectively exposes training data membership without relying on traditional output features.

Contribution

It presents the first MI attack tailored for Re-ID, utilizing similarity distribution analysis and a neural network with anchor selection to improve attack accuracy.

Findings

Effective in Re-ID scenarios

Validates the importance of similarity distribution shift

Works on conventional classification tasks as well

Abstract

While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by membership inference (MI) attack. Most of the existing MI attack algorithms focus on classification models, while Re-ID follows a totally different training and inference paradigm. Re-ID is a fine-grained recognition task with complex feature embedding, and model outputs commonly used by existing MI like logits and losses are not accessible during inference. Since Re-ID focuses on modelling the relative relationship between image pairs instead of individual semantics, we conduct a formal and empirical analysis which validates that the distribution shift of the inter-sample similarity between training and test set is a critical criterion for Re-ID membership inference. As a result, we propose a novel membership inference attack method based on the inter-sample similarity distribution. Specifically, a set of anchor images are sampled to represent the similarity distribution conditioned on a target image, and a neural network with a novel anchor selection module is proposed to predict the membership of the target image. Our experiments validate the effectiveness of the proposed approach on both the Re-ID task and conventional classification task.