FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Shuai Yuan, Guowen Xu, Hongwei Li, Rui Zhang, Xinyuan Qian, Wenbo Jiang, Hangcheng Cao, Qingchuan Zhao

TL;DR
FIGhost introduces a novel physical-world backdoor attack on traffic sign recognition systems using invisible fluorescent ink triggers activated by UV light, achieving high stealth and robustness against defenses.
Contribution
The paper presents the first fluorescent ink-based backdoor attack for physical traffic signs, enhancing stealth, flexibility, and robustness, and supporting multiple attack objectives.
Findings
Effective against state-of-the-art detectors and VLMs
Maintains robustness under environmental variations
Successfully evades existing defenses
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Adversarial Robustness in Machine Learning · Hand Gesture Recognition Systems
