Person Re-identification Method Based on Color Attack and Joint Defence

TL;DR

This paper introduces a novel color variation-based attack on person re-identification systems and proposes a joint defense strategy combining proactive and passive methods to improve robustness against such attacks.

Contribution

It presents a new local transformation attack using color variation and a joint adversarial defense method that enhances contour features and exploits invariance to counteract attacks.

Findings

LTA outperforms existing attack methods in effectiveness.

JAD improves robustness against adversarial attacks.

Experimental results show JAD surpasses state-of-the-art defenses.

Abstract

The main challenges of ReID is the intra-class variations caused by color deviation under different camera conditions. Simultaneously, we find that most of the existing adversarial metric attacks are realized by interfering with the color characteristics of the sample. Based on this observation, we first propose a local transformation attack (LTA) based on color variation. It uses more obvious color variation to randomly disturb the color of the retrieved image, rather than adding random noise. Experiments show that the performance of the proposed LTA method is better than the advanced attack methods. Furthermore, considering that the contour feature is the main factor of the robustness of adversarial training, and the color feature will directly affect the success rate of attack. Therefore, we further propose joint adversarial defense (JAD) method, which include proactive defense and passive defense. Proactive defense fuse multi-modality images to enhance the contour feature and color feature, and considers local homomorphic transformation to solve the over-fitting problem. Passive defense exploits the invariance of contour feature during image scaling to mitigate the adversarial disturbance on contour feature. Finally, a series of experimental results show that the proposed joint adversarial defense method is more competitive than a state-of-the-art methods.