Thesis Details
Mitigation of DoS Attacks Using Machine Learning
Distributed Denial of Service (DDoS) attacks are an ever-increasing type of security incident on modern computer networks. This thesis aims to detect these attacks and provide relevant information in order to mitigate them in real-time. This functionality is achieved by data stream mining and machine learning techniques. The output of the work is a series of tools executing the process of the whole machine learning pipeline - from custom feature extraction through data preprocessing to exporting a trained model ready for deployment. The experimental results evaluated on various real and synthetic datasets indicate an accuracy of over 99% with an ability to reliably detect an ongoing attack within the first 4 seconds of its start.
DoS attack, DDoS attack, DDoS detection, DDoS mitigation, Machine learning, data stream mining
Drábek Vladimír, doc. Ing., CSc. (DCSY FIT BUT), člen
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), člen
@mastersthesis{FITMT23613,
author = "Patrik Goldschmidt",
type = "Master's thesis",
title = "Mitigation of DoS Attacks Using Machine Learning",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2021,
location = "Brno, CZ",
language = "english",
url = "https://www.fit.vut.cz/study/thesis/23613/"
}