Real-Time Intrusion Detection in Automotive Cyber-Physical Systems with Recurrent Autoencoders
Published in Springer Nature, 2023
Recommended citation: V. K. Kukkala, S. V. Thiruloga, and S. Pasricha, "Real-Time Intrusion Detection in Automotive Cyber-Physical Systems with Recurrent Autoencoders," in Machine Learning and Optimization Techniques for Automotive Cyber-Physical Systems, Springer Nature, 2023.
Abstract
Modern vehicles consist of several powerful embedded systems called Electronic Control Units (ECUs), which control different subsystems in the vehicle. The increasing efforts to make vehicles fully autonomous have led to high reliance on information from various external sources, which made the ECUs in the vehicles highly vulnerable to various cyber-attacks. Therefore, it is essential to have a robust detection system in vehicles that can detect various cyber-attacks. To address this issue, in this chapter, we present a novel deep learning-based intrusion detection framework called INDRA that utilizes a Gated Recurrent Unit (GRU) based recurrent autoencoder network to detect various cyber-attacks in automotive cyber-physical systems. Moreover, the INDRA framework is evaluated under different attack scenarios and compared against various state-of-the-art intrusion detection works using a commercially available in-vehicle network dataset.