The field of Person Re-Identification (Re-ID) has received much attention
recently, driven by the progress of deep neural networks, especially for image
classification. The problem of Re-ID consists in identifying individuals
through images captured by surveillance cameras in different scenarios.
Governments and companies are investing a lot of time and money in Re-ID
systems for use in public safety and identifying missing persons. However,
several challenges remain for successfully implementing Re-ID, such as
occlusions and light reflections in people's images. In this work, we focus on
adversarial attacks on Re-ID systems, which can be a critical threat to the
performance of these systems. In particular, we explore the combination of
adversarial attacks against Re-ID models, trying to strengthen the decrease in
the classification results. We conduct our experiments on three datasets:
DukeMTMC-ReID, Market-1501, and CUHK03. We combine the use of two types of
adversarial attacks, P-FGSM and Deep Mis-Ranking, applied to two popular Re-ID
models: IDE (ResNet-50) and AlignedReID. The best result demonstrates a
decrease of 3.36% in the Rank-10 metric for AlignedReID applied to CUHK03. We
also try to use Dropout during the inference as a defense method.

人物再识别（Re-ID）领域受到了深度神经网络的广泛关注，特别是图像分类。本文的焦点在于对 Re-ID 系统进行的对抗攻击，其可能对系统性能构成严重威胁。我们尝试对两种热门 Re-ID 模型（IDE（ResNet-50）和 AlignedReID）应用了两种类型的对抗攻击（P-FGSM 和 Deep Mis-Ranking），并在三个数据集上进行了实验，最佳结果在 Applied to CUHK03 的 AlignedReID 上展示了 Rank-10 度量指标下 3.36% 的降低。我们还尝试通过在推断过程中使用 Dropout 作为一种防御方法。