Controllable Spoofing Attacks on Visual SLAM in Robotic Vehicles
Dec 1, 2025·
,,,,·
1 min read
Yuan Xu
Gelei Deng
Guanlin Li
Xingshuo Han
Shangwei Guo
Tianwei Zhang
Abstract
Visual Simultaneous Localization and Mapping (SLAM) is a critical component in robotic vehicles for navigation and environment mapping. This work presents controllable spoofing attacks that can manipulate Visual SLAM systems to cause navigation errors in robotic vehicles, demonstrating significant security vulnerabilities in current implementations.
Type
Publication
ACM Annual Computer Security Applications Conference (ACSAC)
This work investigates security vulnerabilities in Visual SLAM systems used by robotic vehicles, presenting controllable spoofing attacks that can precisely manipulate vehicle navigation and localization.
