Cross-Modality Perturbation Synergy Attack for Person Re-identification

TL;DR

This paper introduces a universal perturbation attack targeting cross-modality person re-identification systems, effectively disrupting their performance by leveraging gradients from diverse modality data, and highlights the need for improved robustness in such systems.

Contribution

It is the first to explore security vulnerabilities in cross-modality ReID and proposes a novel attack method that considers multiple modalities for enhanced effectiveness.

Findings

The attack significantly degrades cross-modality ReID accuracy.

Experiments on three datasets validate the attack's effectiveness.

Insights for future robustness improvements are provided.

Abstract

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. The code will be available at https://github.com/finger-monkey/cmps__attack.