Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency

Xueping Wang, Shasha Li, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 15097-15107

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 DNNs-based ReID systems. Specifically, three kinds of context inconsistencies caused by adversarial attacks are employed to learn a detector for detecting adversarial attacks, 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 query image, c) the top-K retrievals of a benign query image obtained with multiple expert ReID models tend to be consistent, which is not preserved when attacks are present. Extensive experiments on the Market1501 and DukeMTMC-ReID datasets show that, as the first adversarial attack detection approach for ReID, MEAAD effectively detects various adversarial attacks and achieves high ROC-AUC (over 97.5%).

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2021_ICCV, author = {Wang, Xueping and Li, Shasha and Liu, Min and Wang, Yaonan and Roy-Chowdhury, Amit K.}, title = {Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {15097-15107} }