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

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.

arXiv commentIEEE Signal Processing Magazine (Volume: 38, Issue: 1, Jan. 2021), pp. 42 - 52

References in corpus (5)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
• Fast Feature Fool: A data independent approach to universal adversarial perturbations
• Verification of deep probabilistic models

Cited by in corpus (6)

• Security and privacy for 6G: A survey on prospective technologies and challenges
• On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
• Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfaces
• Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation
• Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces
• Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis