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

TL;DR

This paper investigates the vulnerability of CNN-based semantic segmentation networks used in autonomous driving to adversarial attacks, highlighting the risks and discussing potential defense strategies to improve safety.

Contribution

It provides an analysis of how adversarial perturbations affect CNNs in environment perception and reviews existing defense mechanisms, emphasizing the need for more robust solutions.

Findings

CNNs are highly susceptible to adversarial attacks in semantic segmentation tasks.

Adversarial perturbations can cause significant misperceptions in autonomous driving environments.

Current defense strategies have limitations, requiring further research for robustness.

Abstract

Enabling autonomous driving (AD) can be considered one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception is usually performed by combining the semantic information captured by several sensors, i.e., 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, CNNs constantly showed state-of-the-art performance on several vision-related tasks, such as semantic segmentation of traffic scenes using nothing but the red-green-blue (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 the 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 to clarify the advantages and disadvantages associated with applying CNNs for environment perception in AD to serve as a motivation for future research in this field.