THE UTILIZATION OF MACHINE LEARNING FOR NETWORK INTRUSION DETECTION SYSTEMS

Abstract

This study investigates the integration of Multilayer Perceptron (MLP) architecture in Network Intrusion Detection Systems (NIDS) to strengthen cyber defences against evolving threats. The goal is to explore the potential of MLP in learning complex patterns and adapting to dynamic attack vectors, thereby improving detection accuracy. Key results from 5-fold cross-validation demonstrate model consistency, achieving an average accuracy of 0.97 with minimal standard deviation. Further evaluation across multiple nodes per layer and train-test splits demonstrate model robustness, displaying high metrics such as AUC-ROC and F1-Score. Challenges, such as the scarcity of large labelled datasets and complex model interpretability, are acknowledged. This study provides a comprehensive foundation for future investigations, suggesting potential directions such as integrating advanced neural network architectures and assessing model transferability. In conclusion, this study contributes to the evolving intersection of machine learning and cyber security, offering insights into the strengths, limitations, and future directions of MLP-based NIDS. As cyber threats evolve, continued refinement of MLP methods is critical to effective network defences against sophisticated adversaries.