Tools
Tools
Ali, Abiodun (2022) Anomaly Detection in a Network Intrusion using a Software-defined Network and Deep Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (730kB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Hackers utilize a multi class group of network threats to elude the security mechanisms of networks. The deficiencies of network systems combined with the evolving methods of attack have created opportunities for hackers to exploit network systems. The motivation for the research work originated from the need to identify the best algorithm of Advanced Machine Learning (AML) that will detect network threats.
The study used three different Deep Learning models to investigate the performer at identifying cyber-threats in networks. The Accuracy of the Cu-DNN model across all classes was 97.40%, that of the Cu-GRU model was 98.24%, while the accuracy of the Cu-DNNGRU was 99.11%. The precision of the Cu-DNN model was the lowest with 96%, the Cu-GRU model was 98.64%; and the Cu-GRU model was 98.47%. The Cu-GRU model recorded the lowest Recall with 98.3%, the Cu-DNN model is 98.6%, while the highest Recall score was recorded for the Cu-DNNGRU model with 99.2%. Other performance metrics assessed were the F1-score, false detection rates, and true detection rates. The study concluded that the Cu-DNNGRU was the best of the three models at detecting network threats.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | SDN; threats detection; attacks; Advanced ML; Deep 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 H Social Sciences > HV Social pathology. Social and public welfare > Criminology > Crimes and Offences > Cyber Crime |
| Divisions: | School of Computing > Master of Science in Cyber Security |
| Depositing User: | Clara Chan |
| Date Deposited: | 23 Nov 2022 15:22 |
| Last Modified: | 23 Nov 2022 15:22 |
| URI: | https://norma.ncirl.ie/id/eprint/5927 |
Actions (login required)
 |
View Item |