@Inbook{Restuccia2019,
author="Restuccia, Francesco
and D'Oro, Salvatore
and Zhang, Liyang
and Melodia, Tommaso",
editor="Wang, Cliff
and Lu, Zhuo",
title="The Role of Machine Learning and Radio Reconfigurability in the Quest for Wireless Security",
bookTitle="Proactive and Dynamic Network Defense",
year="2019",
publisher="Springer International Publishing",
address="Cham",
pages="191--221",
abstract="Wireless networks require fast-acting, effective and efficient security mechanisms able to tackle unpredictable, dynamic, and stealthy attacks. In recent years, we have seen the steadfast rise of technologies based on machine learning and software-defined radios, which provide the necessary tools to address existing and future security threats without the need of direct human-in-the-loop intervention. On the other hand, these techniques have been so far used in an ad hoc fashion, without any tight interaction between the attack detection and mitigation phases. In this chapter, we propose and discuss a Learning-based Wireless Security (LeWiS) framework that provides a closed-loop approach to the problem of cross-layer wireless security. Along with discussing the LeWiS framework, we also survey recent advances in cross-layer wireless security.",
isbn="978-3-030-10597-6",
doi="10.1007/978-3-030-10597-6_8",
url="https://doi.org/10.1007/978-3-030-10597-6_8"
}