A Taxonomy of Machine-Learning-Based Intrusion Detection Systems for the Internet of Things: A Survey

Abstract

The Internet of Things (IoT) is an emerging technology that has earned a lot of research attention and technical revolution in recent years. Significantly, IoT connects and integrates billions of devices and communication networks around the world for several real-time IoT applications. On the other hand, cybersecurity attacks on the IoT are growing at an alarming rate since these devices are vulnerable because of their limited battery life, global connectivity, resource-constrained nature, and mobility. When attacks on IoT networks go undetected within a speculated period, such security attacks may prompt severe threats and disruptive behavior inside the network and make the network unavailable to the end user. Hence, it is quintessential to design an intelligent and robust security approach that promptly detects potential attack surfaces in a dynamic IoT network. This article investigates a comprehensive survey of machine learning, deep learning, and reinforcement learning-based intelligent intrusion detection techniques for securing IoT. Also, this article thoroughly illustrates the implementation of various categories of security threats in IoT with a neat diagram. Significantly, we classify the threats into two broad categories: 1) wireless sensor networks (WSNs) inherited security attacks and 2) routing protocol for low power and lossy networks (RPL) specific security attacks in IoT. Finally, we present potential research opportunities and challenges in intelligent intrusion detection approaches in future IoT security.