Deep Learning-Based Adaptive Network Intrusion Detection System (DL-ANIDS) for 5G Mobile Network Security

Developing intrusion detection systems (IDSs) that automatically identify and categorize assaults at network and host levels relies heavily on deep learning methods. Upcoming fifth-generation (5G) mobile technology presents fresh threats to cyber security protection systems due to its improved communication capabilities. Even though new methods have emerged recently, current intrusion detection and protection processes will become outdated if not adjusted for 5G. Hence this paper proposes a deep learning-based adaptive network intrusion detection system (DL-ANIDS) to detect cyber threats in 5G mobile networks with sufficient efficiency and speed. This study presents deep learning algorithms for analyzing network traffic via feature extraction from network flows. In addition, our proposed method enables automated configuration tuning of the cyber defense system (CDS) to handle traffic fluctuations, optimize the computing resources required at any given time, and fine-tune the behavior and performance of analysis and detection processes. This paper investigates using a deep neural network (DNN) to create a versatile and efficient IDS capable of detecting and categorizing unexpected and unanticipated assaults. The experiments demonstrate our architecture’s ability to adjust the anomaly detection system based on real-time data from 5G subscribers’ devices, optimizing resource use.