NORMA eResearch @NCI Library

Flow-Based Network Intrusion Detection using Hybrid Machine Learning Techniques

Ganeshkar, Ashutosh Datta (2024) Flow-Based Network Intrusion Detection using Hybrid Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (4MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (2MB) | Preview

Abstract

Modern network intrusion systems require the detection of breaches to be secure, but it is a difficult task as the network data is diverse and dynamic. By integrating oversampling technique with ensemble Machine Learning methods, this study investigates ways to enhance Intrusion Detection in flow-based data. The purpose of the study is to evaluate how well the hybrid ensemble technique detects the intrusions. The UNSW-NB15 dataset was evaluated to train algorithms such as AdaBoost, XGBoost, Gradient Boosting and Stacking classifier/Hybrid Ensemble. Using SMOTE technique, the class imbalances were addressed by balancing the data. The findings show that, other referenced studies showed accuracy above 90%, the Hybrid Ensemble model performed better with accuracy of 89.59% on balanced data using SMOTE method To identify different network attacks, the results shows that ensemble learning method significantly improves detecting the attacks and accuracy. The advantages of combining different ensemble methods with oversampling technique like SMOTE is very essential. To raise network security, model suggests creating sophisticated detection system with hybrid model. To make sure these solutions are broadly applicable and reliable, the future work should focus on optimizing model parameters and test new methods.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
McLaughlin, Eugene
UNSPECIFIED
Uncontrolled Keywords: Network Intrusion Detection System (NIDS); Machine Learning; SMOTE (Synthetic Minority Oversampling technique); Ensemble Learning; AdaBoost; XGBoost; Gradient Boosting
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
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 29 Jul 2025 16:09
Last Modified: 29 Jul 2025 16:09
URI: https://norma.ncirl.ie/id/eprint/8312

Actions (login required)

View Item View Item