Enhancing Intrusion Detection in Education Sector Through Advanced Machine Learning Techniques: A Comparative Study

Intrusion Detection Systems (IDS) are important for identifying potential security threats, recording relevant data, reporting suspicious activity, and facilitating continuous improvement of security protocols. This study presents an IDS model developed using a range of machine learning (ML) techniques, including Naïve Bayes, Decision Tree, Support Vector Machines (SVM), and Random Forest. Each model's performance was assessed using standard metrics like F1-score, recall, accuracy, and precision. The KDD Cup 99 dataset, which contains a comprehensive set of audit data simulating various types of network intrusions in a military environment, was employed for training and testing the models. The primary objective was to enhance the effectiveness of intrusion detection and safeguard computer networks in the education sector. Deploying an Intrusion Detection System (IDS) in schools and universities improves security by preventing unauthorized access, detecting potential cyber threats, and protecting sensitive information of students and faculty. Results indicate that the Random Forest algorithm, followed closely by SVM and Decision Tree, demonstrated the highest reliability and efficiency in detecting intrusions. The results emphasize the vital significance of carefully choosing machine learning models to enhance cybersecurity resilience in educational infrastructures.