FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
This addresses security risks in autonomous driving systems by providing a stealthy and flexible backdoor attack method, though it is incremental as it builds on existing physical backdoor attack concepts with novel trigger materials.
The paper tackles the vulnerability of traffic sign recognition systems to backdoor attacks by introducing FIGhost, a physical-world attack using fluorescent ink triggers that are invisible under normal light and activated by ultraviolet light, achieving high effectiveness against state-of-the-art detectors and Vision-Large-Language-Models while maintaining robustness and evading defenses.
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.