The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

Abstract

Enabling autonomous driving (AD) can be considered as one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with the environment perception being one of its core functions. Environment perception is usually performed by combining the semantic information captured by several sensors, i.e., light detection and ranging (LiDAR) or camera. The semantic information from the respective sensor can be extracted by using convolutional neural networks (CNNs) for dense prediction. In the past years, CNNs constantly showed state-of-the-art performance on several vision-related tasks, such as semantic segmentation of traffic scenes using nothing but RGB images provided by a camera. Although CNNs obtain state-of-the-art performance on clean images, almost imperceptible changes to the input, referred to as adversarial perturbations, may lead to fatal deception. The goal of this article is to illuminate vulnerability aspects of CNNs used for semantic segmentation with respect to adversarial attacks, and share insights into some of the existing known adversarial defense strategies. We aim at clarifying the advantages and disadvantages coming with applying CNNs for environment perception in AD in order to serve as a motivation for future research in this field.