Robust perception is crucial for autonomous vehicle security. In this work, we design a practical adversarial patch attack against camera-based obstacle detection. We identify that the back of a box truck is an effective attack vector. We also improve attack robustness by considering a variety of input frames associated with the attack scenario. This demo includes videos that show our attack can cause end-to-end consequences on a representative autonomous driving system in a simulator.
Demo #8: Security of Camera-based Perception for Autonomous Driving under Adversarial Attack
Christopher DiPalma, Ningfei Wang, Takami Sato, and Qi Alfred Chen (UC Irvine)
View More Papers
Mohit Kumar Jangid (Ohio State University) and Zhiqiang Lin (Ohio State University)Read More