Logo image
Back
Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
Preprint   Open access

Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective

Ningfei Wang, Shaoyuan Xie, Takami Sato, Yunpeng Luo, Kaidi Xu and Qi Alfred Chen
arXiv.org
15 Sep 2024
DOI: https://doi.org/10.48550/arxiv.2409.09860
url
https://arxiv.org/abs/2409.09860View
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute,  Open

Abstract

Computer Science - Computer Vision and Pattern Recognition Computer Science - Cryptography and Security
Traffic Sign Recognition (TSR) is crucial for safe and correct driving automation. Recent works revealed a general vulnerability of TSR models to physical-world adversarial attacks, which can be low-cost, highly deployable, and capable of causing severe attack effects such as hiding a critical traffic sign or spoofing a fake one. However, so far existing works generally only considered evaluating the attack effects on academic TSR models, leaving the impacts of such attacks on real-world commercial TSR systems largely unclear. In this paper, we conduct the first large-scale measurement of physical-world adversarial attacks against commercial TSR systems. Our testing results reveal that it is possible for existing attack works from academia to have highly reliable (100\%) attack success against certain commercial TSR system functionality, but such attack capabilities are not generalizable, leading to much lower-than-expected attack success rates overall. We find that one potential major factor is a spatial memorization design that commonly exists in today's commercial TSR systems. We design new attack success metrics that can mathematically model the impacts of such design on the TSR system-level attack success, and use them to revisit existing attacks. Through these efforts, we uncover 7 novel observations, some of which directly challenge the observations or claims in prior works due to the introduction of the new metrics.

Metrics

6 Record Views

Details

Logo image