Beyond Universal Person Re-ID Attack

TL;DR

This paper reveals the vulnerability of current person re-identification models to a novel universal adversarial perturbation attack, proposing a more effective method that disrupts similarity rankings across models, highlighting the need for more robust solutions.

Contribution

It introduces MUAP, a new universal adversarial perturbation method for person Re-ID that is both image-agnostic and model-insensitive, with a novel list-wise attack objective.

Findings

MUAP achieves high attack success rates across models.

Current Re-ID models are vulnerable to MUAP.

MUAP outperforms existing attack methods significantly.

Abstract

Deep learning-based person re-identification (Re-ID) has made great progress and achieved high performance recently. In this paper, we make the first attempt to examine the vulnerability of current person Re-ID models against a dangerous attack method, \ie, the universal adversarial perturbation (UAP) attack, which has been shown to fool classification models with a little overhead. We propose a \emph{more universal} adversarial perturbation (MUAP) method for both image-agnostic and model-insensitive person Re-ID attack. Firstly, we adopt a list-wise attack objective function to disrupt the similarity ranking list directly. Secondly, we propose a model-insensitive mechanism for cross-model attack. Extensive experiments show that the proposed attack approach achieves high attack performance and outperforms other state of the arts by large margin in cross-model scenario. The results also demonstrate the vulnerability of current Re-ID models to MUAP and further suggest the need of designing more robust Re-ID models.