Combining Two Adversarial Attacks Against Person Re-Identification Systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Combining Two Adversarial Attacks Against Person Re-Identification Systems

Résumé

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.

Dates et versions

hal-04381614 , version 1 (09-01-2024)

Identifiants

Citer

Eduardo Andrade, Igor Sampaio, Joris Guérin, José Viterbo. Combining Two Adversarial Attacks Against Person Re-Identification Systems. 18th International Conference on Computer Vision Theory and Applications, Feb 2023, Lisbon, France. pp.437-444, ⟨10.5220/0011623800003417⟩. ⟨hal-04381614⟩
9 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More