Adversarial Attacks and Countermeasures on Image Classification-based Deep Learning Models in Autonomous Driving Systems: A Systematic Review

Abstract

The rapid development of artificial intelligence (AI) and breakthroughs in Internet of Things (IoT) technologies have driven the innovation of advanced autonomous driving systems (ADSs). Image classification deep learning (DL) algorithms immensely contribute to the decision-making process in ADSs, showcasing their capabilities in handling complex real-world driving scenarios, surpassing human driving intelligence. However, these algorithms are vulnerable to adversarial attacks, which aim to fool them in real-time decision-making and compromise the reliability of the autonomous driving functions. This systematic review offers a comprehensive overview of the most recent literature on adversarial attacks and countermeasures on image classification DL models in ADSs. The review highlights the current challenges in applying successful countermeasures to mitigating these vulnerabilities. We also introduce taxonomies for categorizing adversarial attacks and countermeasures and provide recommendations and guidelines to help researchers design and evaluate countermeasures. We suggest interesting future research directions to improve the robustness of image classification DL models against adversarial attacks in autonomous driving scenarios.