Cross-Modality Perturbation Synergy Attack for Person Re-identification (2401.10090v5)
Abstract: In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems.
- Adversarial metric attack and defense for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(6):2119–2126, 2020.
- Vulnerability of person re-identification models to metric adversarial attacks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.
- Boosting adversarial attacks with momentum. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9185–9193, 2018.
- Eliminate deviation with deviation for data augmentation and a general multi-modal data learning method. arXiv preprint arXiv:2101.08533, 2021.
- Person re-identification method based on color attack and joint defence. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4313–4322, 2022.
- Explaining and harnessing adversarial examples. In 3rd International Conference on Learning Representations, ICLR 2015, 2015.
- In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017.
- Functional adversarial attacks. Advances in neural information processing systems, 32, 2019.
- Universal perturbation attack against image retrieval. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4899–4908, 2019.
- Universal adversarial perturbations. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.
- Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors, 17(3):605, 2017.
- Learning to reduce dual-level discrepancy for infrared-visible person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 618–626, 2019.
- Transferable, controllable, and inconspicuous adversarial attacks on person re-identification with deep mis-ranking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 342–351, 2020.
- Rgb-infrared cross-modality person re-identification. In Proceedings of the IEEE international conference on computer vision, pages 5380–5389, 2017.
- Towards robust person re-identification by defending against universal attackers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):5218–5235, 2023.
- Dynamic dual-attentive aggregation learning for visible-infrared person re-identification. In European Conference on Computer Vision (ECCV), 2020.
- Visible-infrared person re-identification via homogeneous augmented tri-modal learning. IEEE Transactions on Information Forensics and Security, 16:728–739, 2020.
- Deep learning for person re-identification: A survey and outlook. IEEE transactions on pattern analysis and machine intelligence, 44(6):2872–2893, 2022.
- Lifelong person re-identification via knowledge refreshing and consolidation. In AAAI Conference on Artificial Intelligence, 2023.
- Scalable person re-identification: A benchmark. In Proceedings of the IEEE international conference on computer vision, pages 1116–1124, 2015.
- U-turn: Crafting adversarial queries with opposite-direction features. International Journal of Computer Vision, 131(4):835–854, 2023.
- Camera style adaptation for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
- Learning to adapt invariance in memory for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8):2723–2738, 2021.