NORMA eResearch @NCI Library

An SDN based Machine Learning and Deep Learning model for DDoS attack detection on IoT Network

-, Akash (2022) An SDN based Machine Learning and Deep Learning model for DDoS attack detection on IoT Network. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (930kB) | Preview

Abstract

IoT has been around for more than 30 years now and has been a significant factor in people's lives, and that will continue to be the case in the future as well. Among the most advanced and growing technologies in the world is the Internet of Things. It is important to note that a lot of IoT devices are connected to the internet, and these internet nodes contain a lot of resources. These resources might contain sensitive information, making IoT devices a prime target for cybersecurity attacks. Many attempts have been made to combat the dangers of IoT and improve the network's adaptability and speed. The problem with these techniques is that they have not provided a complete defence to the IoT network from attacks and there has not been any combination of Software based networking with machine learning and deep learning discussed profusely for IoT environment and this reason is why this research proposal is focused on finding a better way to stop or minimize these attacks by using machine learning and deep learning with SDN to make IoT systems adaptive and faster.

The bot-Iot dataset offered by University of New South Wales is used for the proposed model. The model is trained with only DDoS labelled traffic from dataset and goes through feature selection and PCA for better results. Upon testing the model with different algorithms of Machine learning and Deep Learning. It was found that they all produce a similar accuracy with Decision Tree providing 86.359% and all other algorithms were compared. The model also achieves its aim to produce null or negligible False Negative.

Item Type: Thesis (Masters)
Uncontrolled Keywords: DDoS attack detection; CNN; Decision Tree; Random Forest; Gaussian NB; IoT networks
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
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Clara Chan
Date Deposited: 23 Nov 2022 15:02
Last Modified: 23 Nov 2022 15:02
URI: https://norma.ncirl.ie/id/eprint/5925

Actions (login required)

View Item View Item