NORMA eResearch @NCI Library

Detection of Application Layer DDoS Attack Using Logistic Regression

Devassy, Jerry Jockey (2021) Detection of Application Layer DDoS Attack Using Logistic Regression. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (632kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


One of the biggest concerns with respect to online security to many online organizations is a distributed denial of service attack (DDoS). DDoS attacks have been a danger to network/security for over a year and will remain tosbe in the foreseeable future. DDoS attacks in an application layer offer a significant issue to Application server these days. The primary goal of a Web/server is to provide uninterrupted/application layer/services to its legit users. However, a DDoS attack in an application layer disrupts the web server's services/to its normal customers, resulting in massive losses. Furthermore, performing an application layer DDoS attack takes extremely few/resources. The techniques for detecting all sorts of application layer DDoS/attacks are quite sophisticated. To develop a framework that would be effective for detecting application layer DDoS attacks for regular user should be that the browsing activity must be simulated in such a way that the legit users and the attacker can be distinguished. In this research, a technique for detecting application layer DDoS attacks that uses feature learning method such as co-relation coefficient to select the best features that are required to improve the efficiency of the model and reduce the size of the dataset. Later logistic regression is used as a classifier to test the model as well as train the model. The model successfully classifies the web traffic based on its nature as normal or attack traffic and after evaluating the model, the prediction percentage that was obtained from testing the dataset was high as 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: 02 Dec 2022 14:44
Last Modified: 02 Dec 2022 14:44

Actions (login required)

View Item View Item