@Inbook{Comert2023,
author="Comert, Ceren
and Gul, Omer Melih
and Kulhandjian, Michel
and Touazi, Azzedine
and Ellement, Cliff
and Kantarci, Burak
and D'Amours, Claude",
editor="Traore, Issa
and Woungang, Isaac
and Saad, Sherif",
title="Secure Design of Cyber-Physical Systems at the Radio Frequency Level: Machine and Deep Learning-Driven Approaches, Challenges and Opportunities",
bookTitle="Artificial Intelligence for Cyber-Physical Systems Hardening",
year="2023",
publisher="Springer International Publishing",
address="Cham",
pages="123--154",
abstract="With the deployment of new 5G services, many of the critical infrastructures such as connected vehicles, remote healthcare and smart infrastructures will be deployed on radio frequency (RF)- based networks. As such, society will be heavily dependent on the ability to protect these new wireless networks as well as the radio spectrum. Solutions such as artificial intelligence (AI)-based transmitter fingerprinting to identify and track unintended interference sources or malicious actors will be one of the several key technologies required to meet the needs of the next generation wireless networks as this technology is deployed as part of a critical infrastructure (CI). As an example, connected and autonomous vehicles (CAVs) can be considered under these cyber-physical systems and critical infrastructures. As 95 percent of new automobiles are expected to be equipped with vehicle to infrastructure (V2I), vehicle to vehicle (V2V), and other telecommunications capabilities by 2022. To ensure the safety of the public, new and automated techniques are needed to protect CAVs on the road from unintentional or malicious interference. Against these requirements, this chapter presents the state of the art in real time decision support systems for the cyber-physical systems that build on critical infrastructures such as CAVs, through radio fingerprinting solutions. In this chapter, we first present the legacy approaches used to detect, classify and identify a transmitter, and then we move towards the machine and deep learning-based (ML/DL) approaches for transmitter identification using RF fingerprinting techniques. Following upon a comparative study on the open issues, challenges, and opportunities towards ML/DL-driven security of the critical cyber-physical systems through RF fingerprinting.",
isbn="978-3-031-16237-4",
doi="10.1007/978-3-031-16237-4_6",
url="https://doi.org/10.1007/978-3-031-16237-4_6"
}