Can I read ITPatch: An Invisible and Triggered Physical Adversarial Patch against Traffic Sign Recognition on EtoBox?

ITPatch: An Invisible and Triggered Physical Adversarial Patch against Traffic Sign Recognition by Yuan, Shuai; Li, Hongwei; Han, Xingshuo; Xu, Guowen; Jiang, Wenbo; Ni, Tao; Zhao, Qingchuan; Fang, Yuguang is a scholarly article available to read on EtoBox.

What is ITPatch: An Invisible and Triggered Physical Adversarial Patch against Traffic Sign Recognition about?

Physical adversarial patches have emerged as a key adversarial attack to cause misclassification of traffic sign recognition (TSR) systems in the real world. However, existing adversarial patches have poor stealthiness and attack all vehicles indiscriminately once deployed. In this paper, we introduce an invisible and triggered physical adversarial patch (ITPatch) with a novel attack vector, i.e., fluorescent ink, to advance the state-of-the-art. It applies carefully designed fluorescent perturbations to a target sign, an attacker can later trigger a fluorescent effect using invisible ultraviolet light, causing the TSR system to misclassify the sign and potentially resulting in traffic accidents. We conducted a comprehensive evaluation to investigate the effectiveness of ITPatch, which shows a success rate of 98.31% in low-light conditions. Furthermore, our attack successfully bypasses five popular defenses and achieves a success rate of 96.72%.

Author

Yuan, Shuai; Li, Hongwei; Han, Xingshuo; Xu, Guowen; Jiang, Wenbo; Ni, Tao; Zhao, Qingchuan; Fang, Yuguang

Published

2024

Language

EN