COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

A Study on the Effectiveness of Machine Learning Techniques to Detect and Prevent Zero-Day Cyberattacks
by Piazza, Nicholas P., M.S., Utica College, 2020, 48; 28262837
Abstract (Summary)

Previously undiscovered or unknown cyberthreats, known as zero-day attacks, are a serious threat to private organizations, governments, and individuals. The threat these zero-day attacks pose is so great due to the lack of knowledge about the threat and the lack of time to prepare for the threat. Conventional detection and prevention technologies such as signature-based detection and software patching both rely on prior knowledge and time to react to cyberthreats. Machine learning allows for cybersecurity professionals to not be dependent on these constraints. Eliminating the reliance on prior knowledge and response time is a crucial step in detecting, preventing, and combatting zero-day attacks. This work will discuss the threat these zero-day attacks pose to Internet security, explain the benefits of incorporating machine learning techniques into the detection, prevention and combatting of zero-day attacks, and will provide a recommendation of a comprehensive and industry wide defense-in-depth strategy to minimize the potential damage of zero-day attacks.

Indexing (document details)
Advisor: Kratochvil, Daniel, Popyack, Leonard
School: Utica College
Department: Cybersecurity
School Location: United States -- New York
Source: MAI 82/7(E), Masters Abstracts International
Subjects: Computer science, Artificial intelligence, Information Technology, Management, Web Studies
Keywords: Cyberattack, Defense-in-depth, Machine learning, Software vulnerabilities, Zero-day cyberattacks, Internet, Cyberthreats, Private organizations
Publication Number: 28262837
ISBN: 9798569940912
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy