An Efficient Approach to Detect the Attacks in SDN based 5G Network Using fuzzy based XG Boost Algorithm

Abstract

The fifth-generation (5G) network has emerged as a next-generation wireless network in recent times. Software-Defined Networking (SDN) is among of the most rapidly expanding network designs that enables an intelligent and programmed control of network configuration to improve the performance of 5G networks. With the increase in the diversity of 5G networks, there is a growing concern about the security of these networks. When unauthorized users introduce malicious attacks, the performance of the SDN based 5G networks is adversely affected. In view of the growing adaptability of SDN based 5G networks various researchers have investigated the need for an effective technology which can identify security attacks in 5G networks. Despite the availability of different security frameworks for preventing malicious attacks in SDN, it is highly challenging to secure the SDN controller. This research intends to propose an efficient security approach to identify the SDN based attacks in 5G networks using machine learning (ML) algorithms. This study proposes the application of a Fuzzy based XGBoost algorithm to strengthen and simplify the network management process and to secure SDN based 5G networks. The findings indicate that the integration of SDN with the ML algorithm classified different network traffic patterns with high accuracy and improved the attack detection performance in 5G communication systems.