FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915291711143936 |
|---|---|
| author | Yuan, Shuai Xu, Guowen Li, Hongwei Zhang, Rui Qian, Xinyuan Jiang, Wenbo Cao, Hangcheng Zhao, Qingchuan |
| author_facet | Yuan, Shuai Xu, Guowen Li, Hongwei Zhang, Rui Qian, Xinyuan Jiang, Wenbo Cao, Hangcheng Zhao, Qingchuan |
| contents | Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide inflexible attack control, or ignore emerging Vision-Large-Language-Models (VLMs). In this paper, we introduce FIGhost, the first physical-world backdoor attack leveraging fluorescent ink as triggers. Fluorescent triggers are invisible under normal conditions and activated stealthily by ultraviolet light, providing superior stealthiness, flexibility, and untraceability. Inspired by real-world graffiti, we derive realistic trigger shapes and enhance their robustness via an interpolation-based fluorescence simulation algorithm. Furthermore, we develop an automated backdoor sample generation method to support three attack objectives. Extensive evaluations in the physical world demonstrate FIGhost's effectiveness against state-of-the-art detectors and VLMs, maintaining robustness under environmental variations and effectively evading existing defenses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12045 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition Yuan, Shuai Xu, Guowen Li, Hongwei Zhang, Rui Qian, Xinyuan Jiang, Wenbo Cao, Hangcheng Zhao, Qingchuan Computer Vision and Pattern Recognition Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide inflexible attack control, or ignore emerging Vision-Large-Language-Models (VLMs). In this paper, we introduce FIGhost, the first physical-world backdoor attack leveraging fluorescent ink as triggers. Fluorescent triggers are invisible under normal conditions and activated stealthily by ultraviolet light, providing superior stealthiness, flexibility, and untraceability. Inspired by real-world graffiti, we derive realistic trigger shapes and enhance their robustness via an interpolation-based fluorescence simulation algorithm. Furthermore, we develop an automated backdoor sample generation method to support three attack objectives. Extensive evaluations in the physical world demonstrate FIGhost's effectiveness against state-of-the-art detectors and VLMs, maintaining robustness under environmental variations and effectively evading existing defenses. |
| title | FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.12045 |