Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
This addresses security vulnerabilities in autonomous vehicle systems by creating adversarial attacks in simulated environments, but it is incremental as it builds on existing adversarial example research.
The paper tackled the problem of physical adversarial examples for object detectors by generating adversarial patterns on vehicle surfaces to evade detection in the Carla simulator, achieving effective results as demonstrated experimentally.
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.