Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception

TL;DR

This paper introduces 3D-TC2, a method using motion consistency over time to detect LiDAR spoofing attacks in autonomous vehicles, achieving high detection rates and real-time performance.

Contribution

It proposes a novel spatio-temporal verification approach for LiDAR spoofing detection, leveraging motion invariants to identify fake objects in autonomous vehicle perception.

Findings

Over 98% attack detection rate for spoofed vehicles

Recall of 91% for detecting spoofed objects

Real-time detection at 41Hz

Abstract

LiDAR sensors are used widely in Autonomous Vehicles for better perceiving the environment which enables safer driving decisions. Recent work has demonstrated serious LiDAR spoofing attacks with alarming consequences. In particular, model-level LiDAR spoofing attacks aim to inject fake depth measurements to elicit ghost objects that are erroneously detected by 3D Object Detectors, resulting in hazardous driving decisions. In this work, we explore the use of motion as a physical invariant of genuine objects for detecting such attacks. Based on this, we propose a general methodology, 3D Temporal Consistency Check (3D-TC2), which leverages spatio-temporal information from motion prediction to verify objects detected by 3D Object Detectors. Our preliminary design and implementation of a 3D-TC2 prototype demonstrates very promising performance, providing more than 98% attack detection rate with a recall of 91% for detecting spoofed Vehicle (Car) objects, and is able to achieve real-time detection at 41Hz