NORMA eResearch @NCI Library

DDoS Attack prediction and classification at Application Layer for Web protocol using Kmeans – SVM Machine Learning Algorithm

Jaiswar, Ramesh (2021) DDoS Attack prediction and classification at Application Layer for Web protocol using Kmeans – SVM Machine Learning Algorithm. 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 (634kB) | Preview

Abstract

Web servers are normally situated in a highly structured network architecture where they allow access to the external internet through backbones. However, the Application Layer DDoS attacks are real threats for those web servers, particularly for the organizational web servers. The intruder transmits the attack requests using legitimate HTTP requests, making it difficult for the detection systems to classify the attack traffic and legit traffic. This study proposes a novel model for identifying and classifying such attack traffics using semi-supervised machine learning algorithms. The model is applied to the CICIDS 2017 Dataset, which contains Application Layer DDoS attack characteristics. The model is created by using correlation analysis to select features and reduce the dataset's dimension, then applying K-Means Clustering to an unlabeled feature-selected dataset to generate clusters, which are then labeled based on their nature (Benign or Attack label), and finally feeding the labeled clustered dataset to Support Vector Machine to train and test the model. The model successfully classifies web traffic based on its nature (Benign or Attack traffic) and on evaluation the model outperforms on the tested dataset when compared to the available classification algorithms.

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
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: 19 Oct 2021 16:56
Last Modified: 19 Oct 2021 17:07
URI: https://norma.ncirl.ie/id/eprint/5114

Actions (login required)

View Item View Item