Spatial-Temporal Anomaly Detection for Sensor Attacks in Autonomous Vehicles

TL;DR

This paper introduces STAnDS, a spatial-temporal anomaly detection model designed to identify sensor attacks in autonomous vehicles, enhancing security by detecting spoofing and false data injection in ToF devices.

Contribution

The paper presents a novel spatial-temporal anomaly detection approach specifically tailored for sensor attack detection in autonomous vehicle perception systems.

Findings

STAnDS effectively detects multiple attack types in simulated environments.

The model combines residual error spatial detection with time-based change detection.

Results demonstrate improved security for autonomous vehicle sensors.

Abstract

Time-of-flight (ToF) distance measurement devices such as ultrasonics, LiDAR and radar are widely used in autonomous vehicles for environmental perception, navigation and assisted braking control. Despite their relative importance in making safer driving decisions, these devices are vulnerable to multiple attack types including spoofing, triggering and false data injection. When these attacks are successful they can compromise the security of autonomous vehicles leading to severe consequences for the driver, nearby vehicles and pedestrians. To handle these attacks and protect the measurement devices, we propose a spatial-temporal anomaly detection model \textit{STAnDS} which incorporates a residual error spatial detector, with a time-based expected change detection. This approach is evaluated using a simulated quantitative environment and the results show that \textit{STAnDS} is effective at detecting multiple attack types.