Zero-Day Attack Detection with Deep Learning in Networks

Diloglu, Baran (2022) Zero-Day Attack Detection with Deep Learning in Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (7MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

Efficiency and accuracy plays a very important role in order to detect and prevent cyber-attacks before any damage done to system or user. Artificial intelligence is growing exponentially rather than type of cyber-attacks. This might allow us to improve network security using help of AI with investigating previous cyber-attack behaviors. All it needs to be done is experimenting with different deep learning models depending on the previous network records and testing these models by cross checking with different network datasets. Choosing deep learning for evaluation purposes can help us to achieve more efficient system rather than machine learning based intrusion detection systems. Also, used deep learning model’s learning process can come with higher accuracy than previous projects in this area. Biggest advantage of using deep learning models in detection systems, AI model can feed itself to grow during the time with new features and specifications. This will eventually help intrusion detection systems to be ready for new type of attacks or same attacks with different features during the time. Proposed algorithms and analysis will show how accurate cyber-attacks can be detected simultaneously. While creation of neural networks to detect attacks, this research will be helpful to identify what kind of datasets need to be used and how datasets should be seperated individually. Answers will be gathered by creating neural networks with almost same algorithms using mixed and singular attack type based datasets.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence 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:	Tamara Malone
Date Deposited:	19 Dec 2022 15:40
Last Modified:	07 Mar 2023 11:00
URI:	https://norma.ncirl.ie/id/eprint/5999

Actions (login required)

View Item