Physical Adversarial Attack on Vehicle Detector in the Carla Simulator

Overall framework


In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild. Specifically, we proposed to generate adversarial patterns to be applied on vehicle surface so that it’s not recognizable by detectors in the photo-realistic Carla simulator. Our approach contains two main techniques, an Enlarge-and-Repeat process and a Discrete Searching method, to craft mosaic-like adversarial vehicle textures without access to neither the model weight of the detector nor a differential rendering procedure. The experimental results demonstrate the effectiveness of our approach in the simulator.

A technique report, arXiv preprint
Tong WU 吴桐
Tong WU 吴桐
Ph.D. Student

My research interests include 3d vision, long-tailed recognition, and robustness.