An approach for mitigating botnet attack on a large network

Ayuba, Hope Micah (2020) An approach for mitigating botnet attack on a large network. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (708kB) | Preview

Abstract

Botnet attacks and the various techniques of propagation has constantly been a tricky challenge for organizations to control. These attacks usually involve compromised computers and all categories of mischievous actions to cause colossal damage and loss of resources from the victim. There is a need to expose the botnet frequent methods of dissemination by implement machine learning algorithms. This research uses artificial neural networks, logistic regression, and decision tree to develop a server-based botnet detection system that maintains accuracy of 99.90%. The system detects bot/botnet that uses IRC, HTTP, and the P2P protocols by analyzing their data flows and then distinguishes their behavioural patterns on the network. Compare to other papers, this research measures performance using Accuracy, True Positive, False Negative Rate, and Precision. We got the dataset from the Stratosphere datasets repository. The dataset was netted at the Czech Technical University, Prague and these botnet samples comprise dissimilar various communication protocols and achieved different activities. Similarly, the study adheres to rigid data input that does not meet the required data within the trained botnet traffic.
Keywords: Botnet, Detection, Network, Flow, Client, Server, Machine learning.

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 > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Dan English
Date Deposited:	26 Jan 2021 14:12
Last Modified:	26 Jan 2021 14:12
URI:	https://norma.ncirl.ie/id/eprint/4485

Actions (login required)

View Item