"Seeing is not Always Believing": Detecting Perception Error Attacks Against Autonomous Vehicles

作者：Jinshan Liu, Jerry Park · 发表于：IEEE Transactions on Dependable and Secure Computing · 年份：2021 · DOI：10.1109/tdsc.2021.3078111 · 被引用次数：56 · 研究领域：Adversarial Robustness in Machine Learning、Anomaly Detection Techniques and Applications、Autonomous Vehicle Technology and Safety

Due to the great achievements in artificial intelligence, it is predicted that autonomous vehicles with little or even no human involvement will come to market in the near future. Autonomous vehicles are equipped with multiple types of sensors. An autonomous vehicle relies on its sensors to perceive its environment, and this sensory information plays a key role in the vehicle's driving decisions. Hence, ensuring the trustworthiness of the sensor data is crucial for drivers’ safety. In this article, we discuss the impact ofperception error attacks (PEAs)on autonomous vehicles, and propose a countermeasure called LIFE (LIDAR andImage dataFusion for detecting perceptionErrors). LIFE detects PEAs by analyzing the consistency between camera image data and LIDAR data using novel machine learning and computer vision algorithms. The performance of LIFE has been evaluated extensively using the KITTI dataset.