Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
arXiv:2007.16118
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.
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Robust Physical-World Attacks on Deep Learning Models
- Light-Head R-CNN: In Defense of Two-Stage Object Detector
- CenterNet: Keypoint Triplets for Object Detection
- Adversarial Examples that Fool Detectors
- Physical Adversarial Examples for Object Detectors
- Standard detectors aren't (currently) fooled by physical adversarial stop signs
Cited by in corpus (4)
- Physical Adversarial Attack meets Computer Vision: A Decade Survey
- On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
- Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications
- Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses