From Lab to Road: Realizing and Detecting LiDAR Spoofing Attacks Against Autonomous Vehicles at High Speed and Long Distance

Light detection and ranging (LiDAR) sensors play a crucial role in autonomous driving (AD) systems by providing high-resolution 3-D spatial information for object detection and environmental mapping. While LiDAR spoofing attacks using malicious lasers to corrupt point clouds have been demonstrated in controlled settings, their feasibility and impact in real-world AD scenarios remain largely unexplored. We address this gap by developing a novel moving vehicle spoofing (MVS) system that enables precise long-distance tracking through infrared (IR) emission detection from LiDAR sensors, significantly enhancing the detection accuracy over previous vision-based methods. Our system integrates three key components: LiDAR detection and tracking system, the auto-aiming system, and the LiDAR spoofing system. Using the MVS system, we provide the first demonstration of LiDAR spoofing attacks posing a severe threat to real-world AD systems. Our object removal attack achieved a success rate of over 96% against a vehicle traveling at 60 km/h, maintaining its effect within the braking distance (20 m). These results confirm the real-world feasibility of such attacks and provide critical evidence of their potential impact on existing AD technologies. To counter this threat, we proposed the world’s first defense method capable of detecting LiDAR spoofing attacks using raw time-of-flight (ToF) data. Our method uses fast Fourier transform (FFT) to identify attack signatures in the frequency domain, enabling real-time detection and addressing limitations of existing methods, particularly in identifying removal attacks. We achieved a detection rate exceeding 90% against high-frequency removal (HFR) attacks, which threaten even next-generation LiDAR systems. These findings demonstrate the feasibility of real-time LiDAR spoofing detection and the development of robust defenses for AD systems.