Transient Adversarial 3D Projection Attacks on Object Detection in Autonomous Driving
Zhou, Ce, Yan, Qiben, Liu, Sijia
–arXiv.org Artificial Intelligence
Object detection is a crucial task in autonomous driving. While existing research has proposed various attacks on object detection, such as those using adversarial patches or stickers, the exploration of projection attacks on 3D surfaces remains largely unexplored. Compared to adversarial patches or stickers, which have fixed adversarial patterns, projection attacks allow for transient modifications to these patterns, enabling a more flexible attack. In this paper, we introduce an adversarial 3D projection attack specifically targeting object detection in autonomous driving scenarios. We frame the attack formulation as an optimization problem, utilizing a combination of color mapping and geometric transformation models. Our results demonstrate the effectiveness of the proposed attack in deceiving YOLOv3 and Mask R-CNN in physical settings. Evaluations conducted in an indoor environment show an attack success rate of up to 100% under low ambient light conditions, highlighting the potential damage of our attack in real-world driving scenarios.
arXiv.org Artificial Intelligence
Sep-25-2024
- Country:
- North America > United States > Michigan > Ingham County (0.14)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Automobiles & Trucks (1.00)
- Information Technology
- Robotics & Automation (0.81)
- Security & Privacy (0.69)
- Transportation > Ground
- Road (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.46)
- Representation & Reasoning (1.00)
- Robots > Autonomous Vehicles (1.00)
- Vision (1.00)
- Machine Learning > Neural Networks
- Information Technology > Artificial Intelligence