Deep Learning for Intrusion Detection

11Deep Learning-Based Intrusion Detection in Wireless Networks

Shadab Alam¹ and Sadaf Ahmad²

¹Department of Computer Science, College of Engineering and Computer Science, Jazan University, Jazan, Saudi Arabia²Department of Computer Science, Aligarh Muslim University, Aligarh, Uttar Pradesh, India

11.1 Introduction

The modern communication world is inseparably connected to wireless networks. They are essential not only for mobile telephony but also for applications in the Internet of Things (IoT), industrial automation, and cloud computing. However, as in all other domains, the widespread use of wireless technologies has created new cybersecurity problems. Today, criminal hackers and hostile nation-states use more sophisticated methods to achieve better results in stealing and harming [1]. In the case of wireless networks, the basest of these methods involve sending large amounts of packets to deny service to legitimate users. Other methods, like eavesdropping (listening in), databases, and legwork, have also become more manageable for today's cyber gangsters. Moreover, for today's wireless networks, a more significant, faster, and more insatiable storm of packets means that the potential for severe harm increases. Deep learning (DL) is a subdomain of artificial intelligence (AI) that has emerged as a transformative technology for improving intrusion detection systems (IDSs) in wireless networks [2]. Rather than relying on the hand-crafted features that traditional machine learning ...