Breaking the Shield: Systematic Security Analysis on Pulse Fingerprinting LiDAR Systems for Autonomous Driving

Light detection and ranging (LiDAR) sensors play a crucial role in autonomous driving (AD) systems because of their high-definition 3-D sensing capabilities. While LiDAR spoofing attacks that project fake ranging signals pose a critical security threat, new-generation (new-gen) LiDARs have introduced pulse fingerprinting (PF), an authentication mechanism that distinguishes reflected signals from external interference. Although PF offers a promising defense against spoofing attacks, its security implications remain unexplored. This article presents the first comprehensive security evaluation of PF features. While current PF-equipped LiDARs use the time difference of pulse pairs as authentication to counter conventional spoofing attacks, we demonstrate their vulnerability to periodic malicious laser pulses through two novel attacks: high-frequency removal (HFR) and adaptive HFR (A-HFR). The basic HFR attack employs high-frequency laser pulses, while A-HFR incorporates weak synchronization and selective range limiting to prevent laser overheating, achieving spoofing frequencies $25\times $ higher than HFR. Our evaluation of three commercial LiDARs with PF reveals their vulnerability to these attacks, with over 96% of the point cloud data vanishing within the attack target area. Through attack simulations against Autoware using real attack data, we show that successful attacks in over 90% of frames invariably lead to accidents, highlighting significant limitations in current PF implementations. We conclude by proposing enhanced security measures for both AD systems and PF mechanisms.