Synthesizing and Deploying 2D Image Spoofing Attacks Against Vision-Based Autonomous Driving Systems

Li-Chen Cheng, UC Irvine; Sri Hrushikesh Varma Bhupathiraju, University of Florida; Shaoyuan Xie, UC Irvine; Michael Clifford, Toyota InfoTech Labs; Sara Rampazzi, University of Florida; Qi Alfred Chen, UC Irvine

Autonomous Driving (AD) systems with monocular cameras are vulnerable to 2D image spoofing attacks. In this demo, we formally define the threat model and present pipelines for generating synthetic and physical-world attack data to support further analysis and defense development.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.