Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving

Xingshuo Han, Guowen Xu, Yuan Zhou, Xuehuan Yang, Jiwei Li, Tianwei Zhang

Abstract

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data and perceive the environment. However, DNN models are vulnerable to different types of adversarial attacks, which pose significant risks to the security and safety of the vehicles and passengers. One prominent threat is the backdoor attack, where the adversary can compromise the DNN model by poisoning the training samples. Although lots of effort has been devoted to the investigation of the backdoor attack to conventional computer vision tasks, its practicality and applicability to the autonomous driving scenario is rarely explored, especially in the physical world.

Locations

• arXiv (Cornell University) - View - PDF
• Proceedings of the 30th ACM International Conference on Multimedia - View