NORMA eResearch @NCI Library

Providing Network-Centric Data Security Using Machine Learning and Intrusion Detection

Sharma, Komal (2022) Providing Network-Centric Data Security Using Machine Learning and Intrusion Detection. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (607kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (918kB) | Preview


In past few years, sophisticated cyber-attacks are growing day by day because the advancement of computer-based technologies and uses of computer-based applications in human life. Intrusion detection system are used to help in identifying the network layer attacks and provide security. But traditional Intrusion detection systems are not able to detect the novel attacks. Therefore, it become necessary to improve and deploy the intrusion detection system with the help of machine learning (ML) models. This can be done by analysing the intrusive data set.

In this research ensemble-based machine learning models along with intrusion detection system are proposed. The aim of this research is to identify the network-based intrusions by evaluating and comparing the performance of different Ensemble ML models. The performance of these models is measured based on accuracy, F-1 score and Cross-validation Score. In this research Aegean Wi-Fi Intrusion Dataset 3 (AWID3) is used which is newest version of AWID dataset having the data of many types of attacks. The dataset of 8 types of attacks is chosen for this research with 8 different Ensemble based ML models such as Bagging, Adaboost, Random Forest (RF), Extra tree, Gradient Boosting, Isolation Forest (IF), Stacking, and Voting Classifier. These ML models are trained by using the AWID3 dataset and performance of these models are evaluated. The results of models show that among all of models Random Forest, Extra tree classifier, and Voting classifier performed very well on AWID3 datset with a 100% accuracy, 100% F-1 score and 100% cross-validation score. That means these three models are most accurate to identify the network-based intrusion attacks.

Item Type: Thesis (Masters)
Uncontrolled Keywords: AWID3 dataset; Intrusion detection system; Ensemble machine learning
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: Tamara Malone
Date Deposited: 29 Dec 2022 16:02
Last Modified: 07 Mar 2023 12:13

Actions (login required)

View Item View Item