DoS Attack Detection and Mitigation through Deep Learning Techniques

Gupta, Saurabh Sanjayprasad (2023) DoS Attack Detection and Mitigation through Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (957kB) | Preview

Abstract

In the realm of cybersecurity, the increasing occurrence of Denial-of-Service (DOS) attacks has presented significant hurdles in ensuring that online services remain consistently accessible. This report focuses on the critical task of identifying and mitigating DOS attacks, employing advanced techniques from the field of Deep Learning. Specifically, we employ a specialized neural network called Convolutional Long Short-Term Memory (CLSTM) as the primary tool for categorizing and detecting DOS attacks. For benchmarking purposes, we also utilize the Support Vector Machine (SVM), a widely used machine learning approach. The study involves a detailed analysis of data from network traffic, which we break down into four distinct classes: Benign (normal activity), MSSQL, Syn (SYN flood attacks), and UDP (UDP flood attacks), each representing different attack scenarios. Utilizing the capabilities of deep learning, we train the CLSTM algorithm to recognize and classify these classes with an exceptional level of accuracy. Our initial experimental findings showcase an impressive detection accuracy of 98.91% using the CLSTM model, reaffirming its effectiveness in addressing DOS attacks. In comparison, the SVM model achieves a detection accuracy of 75.42%, highlighting the superior performance of the CLSTM approach.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Aleburu, Joel UNSPECIFIED
Uncontrolled Keywords:	Denial-of-Service (DOS) Attacks; Deep Learning; Convolutional Long Short-Term Memory (CLSTM); SVM
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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Tamara Malone
Date Deposited:	22 Oct 2024 11:32
Last Modified:	22 Oct 2024 11:32
URI:	https://norma.ncirl.ie/id/eprint/7121

Actions (login required)

View Item