A Deep Learning approach for Cyber Threat Detection using Intrusion Detection Data

Bhogate, Mayuri Ganpat (2024) A Deep Learning approach for Cyber Threat Detection using Intrusion Detection Data. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (944kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This paper is a systematic review of the deep learning models and their effectiveness in detecting emerging cyber threats, specifically focusing on Distributed Denial of Service (DDoS) attack using balanced data obtained from Kaggle. CNN, LSTM, BiLSTM, and a novel methodology proposed in the study namely Stacked BiLSTM with Self-Attention Mechanism are analyzed. This research is motivated by the fact that the current and emerging cyber threats are complex and usually escape both conventional detection systems. The primary purpose is to optimize the detection accuracy and improve adaptability of cyber threat detection system. It proved that the proposed model, Stacked BiLSTM with Self-Attention Mechanism has better results compared to other models, where classification accuracy is up to 98.39% while CNN achieved 58%, LSTM achieved 55%, and BiLSTM achieved 96%. Based on these findings, there is an indication that with the help of self-attention mechanisms, it is possible to pay more attention to key elements and enhance real-time detection in various environments. By offering a detailed and effective solution to cyber threat identification, this research brings an important value to the literature and has clear application in improving counter measures against complex cyber threats.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Singh, Jaswinder 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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	11 Aug 2025 15:25
Last Modified:	11 Aug 2025 15:29
URI:	https://norma.ncirl.ie/id/eprint/8496

Actions (login required)

View Item