Robust Intrusion Detection Systems for In-Vehicle Networks in Autonomous Vehicles - A Machine Learning Perspective: Develops robust intrusion detection systems for in-vehicle networks in AVs, utilizing machine learning techniques

Abstract

In recent years, the automotive industry has witnessed a rapid evolution towards autonomous vehicles (AVs), which heavily rely on in-vehicle networks for communication and operation. However, the increasing connectivity and complexity of these networks have exposed them to various cyber threats, including intrusion attempts. To ensure the safety and security of AVs, robust intrusion detection systems (IDS) are essential. This paper presents a comprehensive review of existing IDS for in-vehicle networks and proposes a novel approach based on machine learning techniques to enhance the robustness of IDS in AVs. We discuss the challenges and limitations of current IDS, and then delve into the application of machine learning algorithms for intrusion detection. Experimental results demonstrate the effectiveness of our proposed approach, highlighting its potential to significantly improve the security of in-vehicle networks in autonomous vehicles.