Kasman, Sachlany and Lukas, Lukas and Lim, Charles (2021) Spectral Analysis of DDoS Pre-Attack with Fourier Transform. Masters thesis, Swiss German University.

Preview	Text Sachlany Kasman 21951016 TOC.pdf Download (1MB) | Preview
	Text Sachlany Kasman 21951016 1.pdf Restricted to Registered users only Download (1MB)
	Text Sachlany Kasman 21951016 2.pdf Restricted to Registered users only Download (1MB)
	Text Sachlany Kasman 21951016 5.pdf Restricted to Registered users only Download (261kB)
	Text Sachlany Kasman 21951016 4.pdf Restricted to Registered users only Download (2MB)
	Text Sachlany Kasman 21951016 3.pdf Restricted to Registered users only Download (1MB)
Preview	Text Sachlany Kasman 21951016 Ref.pdf Download (857kB) | Preview

Abstract

Analyzing Distributed Denial of Service (DDoS) pre-attack and anomaly detection in Machine Learning (ML) has profoundly popular in academic research, intrusion prevention system, and DDoS detection. ML algorithms, computer vision, and digital signaling processing in the cybersecurity field have improved significantly. As a result, specific technique and method for detecting and analyzing attack have introduced. For this reason, we propose a technique of digital signaling processing and ML for detecting attack of DDoS. Further, leveraging Fourier Transform in ML computation effort reduces computational cost and complexity for deploying effective and efficient DDoS Defense. Spectral analysis is a method to discretely quantify spectrum and frequencies for extracting attack features from the data-set. This research proposes a technique and methodology that leverages filtering, convolution, spectral analysis with Fourier Transform that distinguish multi-classes attack into the taxonomy of NSL-KDD data-set. Our research achieves 98-99% accuracy compared to previous work. Further, the techniques help security researchers and analysts reduce ever-evolved adversaries’ threats to develop an effective defensive strategy towards future attacks.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Fast Fourier Transform, Discrete Fourier Transform, FFT, DFT, Spectrogram, Spectral Analysis, Digital Signaling Process, Convolution
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning T Technology > T Technology (General) > T58.5 Information technology
Divisions:	Faculty of Engineering and Information Technology > Department of Information Technology
Depositing User:	Faisal Ifzaldi
Date Deposited:	05 Jan 2022 10:07
Last Modified:	05 Jan 2022 10:07
URI:	http://repository.sgu.ac.id/id/eprint/2300

Actions (login required)

View Item