NETWORK INTRUSION DETECTION USING SUPERVISED MACHINE LEARNING TECHNIQUE WITH FEATURED SELECTION

Abstract

The rapid growth of computer networks, cloud computing, Internet of Things (IoT), and online services has increased the exposure of network infrastructures to cyber threats. Traditional signature-based intrusion detection systems are effective against known attacks but have limited capability to identify evolving and previously unseen threats. This work proposes a Network Intrusion Detection System (NIDS) based on supervised machine learning techniques integrated with feature selection to improve detection performance and computational efficiency. Network traffic data from benchmark datasets, including NSL-KDD, UNSW-NB15, and CIC-IDS2017, are processed through data cleaning, missing-value treatment, duplicate removal, normalization, and categorical encoding. Feature selection techniques are applied to eliminate irrelevant and redundant attributes and reduce the dimensionality of network traffic data. The selected features are used to train and evaluate Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Artificial Neural Network (ANN), and k-Nearest Neighbors (KNN) classifiers for distinguishing normal and malicious network traffic. The trained models are integrated into an intrusion detection module for traffic classification and alert generation. Detected events and security information are stored in a database and presented through a web-based dashboard. The proposed approach aims to improve detection accuracy, reduce false alarms, decrease computational complexity, and support scalable and effective network security monitoring. Keywords: Network Intrusion Detection System, Supervised Machine Learning, Cybersecurity, Network Traffic Analysis, Support Vector Machine.