mlsanityData to 14 Oct 2026

Combining Two Adversarial Attacks Against Person Re-Identification Systems

arXiv 2309.13763 ↗First posted 24 Sep 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 24 Sep 2023.

Builds on

18 of 37 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  5. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  6. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 692
  7. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  8. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 430
  9. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  10. 2016Person Re-identification: Past, Present and Futurecited by 181
  11. 2016A Discriminatively Learned CNN Embedding for Person Re-identificationcited by 78
  12. 2017AlignedReID: Surpassing Human-Level Performance in Person Re-Identificationcited by 61
6 more
  1. 2020Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Rankingcited by 42
  2. 2019advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patternscited by 35
  3. 2015Deep Feature Learning with Relative Distance Comparison for Person Re-identificationcited by 25
  4. 2018Query Attack via Opposite-Direction Feature:Towards Robust Image Retrievalcited by 7
  5. 2020Towards Practical Implementations of Person Re-Identification from Full Video Framescited by 3
  6. 2018Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identificationcited by 1

Built on by

Not cited yet.