VisionGuard: Secure and Robust Visual Perception of Autonomous Vehicles in Practice
Oct 14, 2024·,,
,,,,·
1 min read
Xingshuo Han
Haozhao Wang
Kangqiao Zhao
Gelei Deng
Yuan Xu
Hangcheng Liu
Han Qiu
Tianwei Zhang
Abstract
Autonomous vehicles rely heavily on visual perception systems for navigation and decision-making. However, these systems are vulnerable to various adversarial attacks that can compromise vehicle safety. This work presents VisionGuard, a comprehensive framework for securing and robustifying visual perception in autonomous vehicles against real-world attacks.
Type
Publication
ACM Conference on Computer and Communications Security (CCS)
VisionGuard presents a practical approach to securing visual perception systems in autonomous vehicles, addressing critical vulnerabilities that could be exploited by adversaries in real-world scenarios.
