Botnet Detection Using Multi-D Convolutional Neural Network

Srinivasan, Shalini (2023) Botnet Detection Using Multi-D Convolutional Neural Network. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

DDoS attacks pose a significant threat to the network of every organisation. The damage caused by DDoS on a renowned company Bandwidth Inc. was around 10 million for a fiscal year.1 And, as cybercriminals are building more and more sophisticated botnets, there is need for newer techniques, therefore, this paper presents an approach for the detection of HTTP, IRC, and P2P botnets. The dataset used is CTU 13 containing 13 different scenarios to study upon. To avoid any false positives, the data is further categorised based on the flow information in bytes. After the pre-processing of the data, a unique approach of CNN called Multi-D CNN model is considered, that detects legitimate, suspicious, or malicious traffic. Upon analysis, it was concluded that using categorical prediction, the Multi-D CNN model has an accuracy of 73.5%.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas 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 > 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:	Tamara Malone
Date Deposited:	06 Nov 2024 17:20
Last Modified:	06 Nov 2024 17:20
URI:	https://norma.ncirl.ie/id/eprint/7155

Actions (login required)

View Item