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 stateof-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.

中文翻译：

---

自动驾驶中语义分割网络对对抗性攻击的脆弱性：增强广泛的环境感知

实现自动驾驶 (AD) 可被视为当今技术的最大挑战之一。AD 是一项由多个功能完成的复杂任务，其中环境感知是其核心功能之一。环境感知通常是通过组合多个传感器（即激光雷达或摄像头）捕获的语义信息来执行的。可以通过使用卷积神经网络 (CNN) 进行密集预测来提取来自各个传感器的语义信息。过去，CNN 一直在几个与视觉相关的任务上表现出最先进的性能，例如仅使用相机提供的红绿蓝 (RGB) 图像对交通场景进行语义分割。尽管 CNN 在干净的图像上获得了最先进的性能，但几乎察觉不到输入的变化，被称为对抗性扰动，可能会导致致命的欺骗。本文的目的是阐明用于语义分割的 CNN 与对抗性攻击相关的脆弱性方面，并分享对一些现有已知对抗性防御策略的见解。我们旨在阐明在 AD 中将 CNN 应用于环境感知的优缺点，以作为该领域未来研究的动力。