Explainable Security in SDN-Based IoT Networks

Abstract

The significant advances in wireless networks in the past decade have made a variety of Internet of Things (IoT) use cases possible, greatly facilitating many operations in our daily lives. IoT is only expected to grow with 5G and beyond networks, which will primarily rely on software-defined networking (SDN) and network functions virtualization for achieving the promised quality of service. The prevalence of IoT and the large attack surface that it has created calls for SDN-based intelligent security solutions that achieve real-time, automated intrusion detection and mitigation. In this paper, we propose a real-time intrusion detection and mitigation solution for SDN, which aims to provide autonomous security in the high-traffic IoT networks of the 5G and beyond era, while achieving a high degree of interpretability by human experts. The proposed approach is built upon automated flow feature extraction and classification of flows while using random forest classifiers at the SDN application layer. We present an SDN-specific dataset that we generated for IoT and provide results on the accuracy of intrusion detection in addition to performance results in the presence and absence of our proposed security mechanism. The experimental results demonstrate that the proposed security approach is promising for achieving real-time, highly accurate detection and mitigation of attacks in SDN-managed IoT networks.

Keywords

• SDN
• security
• machine learning
• 5G
• IoT
• intrusion detection