ABSTRACT
The Internet of Things (IoT) and related technologies have become very popular in the past few years. IoT has helped artificial intelligence (AI)-based systems attain more advancement and efficiency by providing an enormous amount of data for model training and inference. Under such circumstances and trends, the traditional cloud computing model faces challenges in handling the huge amounts of data generated by IoT devices to meet practical needs. Edge computing is also one of the emerging technologies, which is used as a mode of communication for intelligent machines, such as sensors and other related devices. The vital role of edge computing is to improve efficiency and reduce latency. These edge devices are connected for the transmission of data to various supply chain services using the IoT. Multiple devices in edge computing frameworks are positioned in compound networks to maintain active functionalities of a complex framework that controls, communicates, and monitors the entire system. However, these communication devices lead to heavy data traffic, and security-related issues occur at edge nodes. In such a situation, an intrusion detection system (IDS) emerges to detect intrusion attacks in edge-enabled networks. The use of machine learning and deep learning techniques is employed to identify various kinds of network intruders. Apart from that, various state-of-the-art contributions relate to an intrusion detection system at edge-enabled devices for identifying data traffic-related issues. Despite all such efforts, numerous complications are raised by intrusion attacks, making it difficult to implement an efficient and effective framework for edge-enabled devices to transfer information throughout all networks. The chapter thus discusses the various applications, challenges, and future directions of IDS using edge-enabled devices, which would provide explicit knowledge on IDS systems to the readers opening the wider scope of future research.
