Optimising Real-Time Threat Detection: A Hybrid SVM and ANN Approach

Narasimhamurthy, Chethanprasad (2023) Optimising Real-Time Threat Detection: A Hybrid SVM and ANN Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (608kB) | Preview
Preview	PDF (Configuration Manual) Download (339kB) | Preview

Abstract

Real-time threat detection poses a significant challenge in the realm of cybersecurity. Recognizing abnormal activities requires advanced monitoring systems. This research introduces a hybrid threat detection model, merging Support Vector Machine (SVM) and Artificial Neural Network (ANN), to address the limitations of conventional monitoring systems. The model, designed for real-time threat detection, leverages SVM for feature extraction and ANN for pattern recognition, providing an innovative solution to evolving security landscapes.

Evaluations using UNSW-NB151 and NSL-KDD2 datasets demonstrate the hybrid model’s superior performance compared to a Logistic Regression model. The hybrid model exhibits higher accuracy of 94.83% for UNSW-NB151 and 95.36% for NSL-KDD2 as compared to Logistic Regression model with accuracy of 93.85% for UNSW-NB151 and 94.48% for NSL-KDD2 for contributing valuable benchmarks to intrusion detection methodologies. The SVM-ANN hybrid model, proven to be robust and adaptable, holds practical implications for effective intrusion detection. However, variations in execution times and the trade-off between false negatives and detection rates warrant further investigation.

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 > Algebra > Algorithms > Computer algorithms 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:	21 Apr 2025 11:33
Last Modified:	21 Apr 2025 11:33
URI:	https://norma.ncirl.ie/id/eprint/7450

Actions (login required)

View Item