Novel Approach in Intrusion Detection Systems Using Mutual Information-based Gradient Boosting Machine

Kachhap, Benhur (2023) Novel Approach in Intrusion Detection Systems Using Mutual Information-based Gradient Boosting Machine. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (628kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study aims to improve the performance of intrusion detection systems (IDS) by implementing the Mutual Information-based Gradient Boosting Machine (MIGBM) feature selection approach. The significance of this study arises from the increasing sophistication of cyberattacks, highlighting the urgent need to innovate and strengthen IDS capabilities. Although numerous scholars have put forth a plethora of approaches to enhance the identification of unauthorized access attempts, this paper introduces a conceptual technique that leverages the utilization of mutual information (MI) feature selection. MIGBM was rigorously tested as a unique feature selection technique to enhance detection accuracy while simultaneously lowering computing time. The objective is to compare the top-performing techniques across multiple performance metrics—recall, precision, classification accuracy, and F1 score with MIGBM with and without MI feature selection. Each method is also critically evaluated based on its limitations. The evaluation involves generating confusion matrices to assess the system's performance, utilizing an updated and pertinent dataset. The leading approach demonstrated MIGBM with an impressive 95% accuracy, just 2% lower than the baseline approach, showcasing remarkable efficiency and precision with a notable timeframe reduction of 40%.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	17 Apr 2025 11:24
Last Modified:	17 Apr 2025 11:24
URI:	https://norma.ncirl.ie/id/eprint/7440

Actions (login required)

View Item