Multi-expert Adversarial Attack Detection In Person Re-identification Using Context Inconsistency

Abstract

The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID). However, ReID systems inherit the vulnerability of DNNs to malicious attacks of visually inconspicuous adversarial perturbations. Detection of adversarial attacks is, therefore, a fundamental requirement for robust ReID systems. In this work, we propose a Multi-Expert Adversarial Attack Detection (MEAAD) approach to achieve this goal by checking context inconsistency, which is suitable for any DNN-based ReID systems. Specifically, three kinds of context inconsistencies caused by adversarial attacks are employed to learn a detector for distinguishing the perturbed examples, i.e., a) the embedding distances between a perturbed query person image and its top-K retrievals are generally larger than those between a benign query image and its top-K retrievals, b) the embedding distances among the top-K retrievals of a perturbed query image are larger than those of a benign q

Stats

• citations35
• S2 citations—
• github stars0
• HF likes0
• heat score11.67
• arxiv keywang2021multi

Related papers

• Cross-entropy Adversarial View Adaptation For Person Re-identification (2019)12.93
• Adaptive Re-ranking Of Deep Feature For Person Re-identification (2018)0.00
• Dynamic Dual-attentive Aggregation Learning For Visible-infrared Person Re-identification (2020)19.67
• Neighbor-based Feature And Index Enhancement For Person Re-identification (2025)0.00
• Deep Co-attention Based Comparators For Relative Representation Learning In Person Re-identification (2018)13.34
• Devil's In The Details: Aligning Visual Clues For Conditional Embedding In Person Re-identification (2020)0.00
• Deep Constrained Dominant Sets For Person Re-identification (2019)9.23
• Mdreid: Modality-decoupled Learning For Any-to-any Multi-modal Object Re-identification (2025)0.00