Network Traffic Anomaly Detection with Deep Learning

Alex, Christy (2024) Network Traffic Anomaly Detection with Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (759kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The increasing rate in cyber threats makes a considerable threat to traditional security features, which makes anomaly detection a crucial step in defending the network from threats. Conventional rules-based Intrusion detection system and Intrusion prevention systems most time fails to detect and prevent latest and evolving threats, which asks for the adoption of more intelligent and adaptive techniques. This research explores the implementation of a machine learning based approach based on autoencoder models to detect the malicious traffic in the network by analysis the usual working the network. The autoencoder model is trained exclusively on the regular traffic, allowing it to distinguish between regular and malicious traffic. The Research through test results suggests the use of encoder models with better thresholding for anomaly detection a autoencoder model configured to work alone would only give reduced efficiency and accuracy.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Verma, Rohit 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 Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	18 Jul 2025 09:08
Last Modified:	18 Jul 2025 09:08
URI:	https://norma.ncirl.ie/id/eprint/8186

Actions (login required)

View Item