Cyber based Intrusion Detection Monitoring System Using Machine Learning

Abstract

The rise of cyber-attacks presents significant challenges in securing digital networks. This paper proposes an Intrusion Detection System (IDS) leveraging Machine Learning (ML) techniques to classify network traffic as normal or malicious. The system utilizes the NSL-KDD dataset, a benchmark for evaluating IDS performance, to train and test various ML models, including K-Nearest Neighbors, Naïve Bayes, Decision Tree, Random Forest, and Logistic Regression. Among these, Random Forest is anticipated to achieve optimal accuracy due to its robust ensemble learning capabilities. A user-friendly web interface enables real-time interaction, allowing users to input network traffic data and obtain security insights. Future enhancements include optimization techniques, cloud-based deployment, and real-time monitoring to transition from prototype to practical application. This IDS aims to strengthen cyber security defenses while minimizing costs associated with cyber intrusions.