An Intrusion Detection Method for Mobile Networks Utilizing Deep Learning Techniques

Abstract

Mobile networks, particularly mobile ad-hoc networks (MANETs), are increasingly deployed in dynamic environments such as military operations, disaster recovery, and remote sensing. However, their decentralized structure, mobility, and open wireless medium make them susceptible to various security threats. This paper presents an intrusion detection method leveraging deep learning techniques to enhance the security of mobile networks. The proposed model uses a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to effectively learn spatial and temporal patterns of network behavior. By analyzing real-time traffic data, the system can accurately detect anomalies and classify different types of attacks such as blackhole, wormhole, and denial-of-service (DoS). Experimental results demonstrate improved detection accuracy and reduced false positive rates compared to traditional machine learning methods. The deep learning-based approach offers adaptability, scalability, and robustness, making it suitable for real-world deployment in mobile network environments.