Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.17026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912133779816448 |
|---|---|
| author | Yang, Jinghan |
| author_facet | Yang, Jinghan |
| contents | The classification of road signs by autonomous systems, especially those reliant on visual inputs, is highly susceptible to adversarial attacks. Traditional approaches to mitigating such vulnerabilities have focused on enhancing the robustness of classification models. In contrast, this paper adopts a fundamentally different strategy aimed at increasing robustness through the redesign of road signs themselves. We propose an attacker-agnostic learning scheme to automatically design road signs that are robust to a wide array of patch-based attacks. Empirical tests conducted in both digital and physical environments demonstrate that our approach significantly reduces vulnerability to patch attacks, outperforming existing techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17026 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RED: Robust Environmental Design Yang, Jinghan Computer Vision and Pattern Recognition The classification of road signs by autonomous systems, especially those reliant on visual inputs, is highly susceptible to adversarial attacks. Traditional approaches to mitigating such vulnerabilities have focused on enhancing the robustness of classification models. In contrast, this paper adopts a fundamentally different strategy aimed at increasing robustness through the redesign of road signs themselves. We propose an attacker-agnostic learning scheme to automatically design road signs that are robust to a wide array of patch-based attacks. Empirical tests conducted in both digital and physical environments demonstrate that our approach significantly reduces vulnerability to patch attacks, outperforming existing techniques. |
| title | RED: Robust Environmental Design |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.17026 |