Adversarial Attacks on Traffic Sign Recognition: A Survey
This is an incremental survey that addresses security vulnerabilities in autonomous driving perception systems.
The paper surveys adversarial attacks on traffic sign recognition systems, which are critical for autonomous vehicles and rely on deep neural networks, highlighting the feasibility of such attacks in both digital and real-world scenarios.
Traffic sign recognition is an essential component of perception in autonomous vehicles, which is currently performed almost exclusively with deep neural networks (DNNs). However, DNNs are known to be vulnerable to adversarial attacks. Several previous works have demonstrated the feasibility of adversarial attacks on traffic sign recognition models. Traffic signs are particularly promising for adversarial attack research due to the ease of performing real-world attacks using printed signs or stickers. In this work, we survey existing works performing either digital or real-world attacks on traffic sign detection and classification models. We provide an overview of the latest advancements and highlight the existing research areas that require further investigation.