Automatic Intrusion Detection System Using Deep Re-Enforcement Learning With Q-network Algorithm (DQN)

Nwokedi, Ugochukwu Ikenna (2023) Automatic Intrusion Detection System Using Deep Re-Enforcement Learning With Q-network Algorithm (DQN). Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

IDS is an important part of the cybersecurity and IT space. Network intrusions are most times very hard to detect and group into their right network patterns. Due to the complexity of network intrusion detection, new age machine learning models that could eliminate some problems that an IDS places on a machine learning model e.g. poorly constructed, non-uniform datasets have to be discovered. Reinforcement learning has been applied to varying successful degrees in automation, gaming etc., and this report shows that it can be successfully applied to the field of network intrusion detection as well. Our proposed model uses the algorithm of a Q-network to operate in a reinforcement learning environment. The approach will be evaluated using a reward against episodes learning curve and will be further compared to more traditional machine learning models that use accuracy, recall and precision as evaluation metrics.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Prior, Michael 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 T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks 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:	Tamara Malone
Date Deposited:	05 Nov 2024 10:44
Last Modified:	05 Nov 2024 10:44
URI:	https://norma.ncirl.ie/id/eprint/7141

Actions (login required)

View Item