TPatch: A Triggered Physical Adversarial Patch
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914625871675392 |
|---|---|
| author | Zhu, Wenjun Ji, Xiaoyu Cheng, Yushi Zhang, Shibo Xu, Wenyuan |
| author_facet | Zhu, Wenjun Ji, Xiaoyu Cheng, Yushi Zhang, Shibo Xu, Wenyuan |
| contents | Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe driving decisions. Existing works have demonstrated the feasibility of fooling the perception models such as object detectors and image classifiers with printed adversarial patches. However, most of them are indiscriminately offensive to every passing autonomous vehicle. In this paper, we propose TPatch, a physical adversarial patch triggered by acoustic signals. Unlike other adversarial patches, TPatch remains benign under normal circumstances but can be triggered to launch a hiding, creating or altering attack by a designed distortion introduced by signal injection attacks towards cameras. To avoid the suspicion of human drivers and make the attack practical and robust in the real world, we propose a content-based camouflage method and an attack robustness enhancement method to strengthen it. Evaluations with three object detectors, YOLO V3/V5 and Faster R-CNN, and eight image classifiers demonstrate the effectiveness of TPatch in both the simulation and the real world. We also discuss possible defenses at the sensor, algorithm, and system levels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00148 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | TPatch: A Triggered Physical Adversarial Patch Zhu, Wenjun Ji, Xiaoyu Cheng, Yushi Zhang, Shibo Xu, Wenyuan Cryptography and Security Computer Vision and Pattern Recognition Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe driving decisions. Existing works have demonstrated the feasibility of fooling the perception models such as object detectors and image classifiers with printed adversarial patches. However, most of them are indiscriminately offensive to every passing autonomous vehicle. In this paper, we propose TPatch, a physical adversarial patch triggered by acoustic signals. Unlike other adversarial patches, TPatch remains benign under normal circumstances but can be triggered to launch a hiding, creating or altering attack by a designed distortion introduced by signal injection attacks towards cameras. To avoid the suspicion of human drivers and make the attack practical and robust in the real world, we propose a content-based camouflage method and an attack robustness enhancement method to strengthen it. Evaluations with three object detectors, YOLO V3/V5 and Faster R-CNN, and eight image classifiers demonstrate the effectiveness of TPatch in both the simulation and the real world. We also discuss possible defenses at the sensor, algorithm, and system levels. |
| title | TPatch: A Triggered Physical Adversarial Patch |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.00148 |