Physical Adversarial Attack on Vehicle Detector in the Carla Simulator

TL;DR

This paper presents a novel method for creating physical adversarial patterns on vehicles that deceive object detectors in the Carla simulator, highlighting vulnerabilities in autonomous vehicle perception systems.

Contribution

It introduces a new approach combining Enlarge-and-Repeat and Discrete Searching techniques to generate adversarial vehicle textures without needing model details or differential rendering.

Findings

Adversarial patterns successfully fool detectors in the Carla simulator.

The approach does not require access to model weights or differential rendering.

Experimental results confirm the effectiveness of the adversarial textures.

Abstract

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.