Software-Defined Intrusion Detection System for DDoS Attacks in IoT Edge Networks

The rapid advance of the Internet of Things (IoT) has led to the emergence of various applications, such as smart healthcare, smart transportation, smart grid, and more. However, IoT consists of resource-constrained smart devices with limited storage and processing capabilities. Against this backdrop, the edge computing paradigm is considered as one of the promising technologies to improve system performance; here integrating edge computing with the IoT solves the computational and processing problems of IoT devices. Despite the wide usage of this integration, new challenges have emerged in security provisioning since traditional security schemes for the Internet are difficult to apply for different IoT-based applications. Thus, in this paper, software-defined networking (SDN) technology is adopted to address this issue and we propose a novel software-defined intrusion detection framework against Distributed Denial of Service (DDoS) attacks in IoT edge networks. In the proposed framework, first, we introduce a three-layer system architecture through an efficient collaboration between the SDN controller and edge servers. Second, we define different types of DDoS attacks and analyze their characteristics. Third, we propose an intrusion detection algorithm and provide a comparative analysis to enhance accuracy performance. By doing this, we also define the best parameters of different classifiers. Experimental results show that our proposed framework can achieve superior accuracy performance to identify DDoS attacks and enhance the security of IoT edge networks.