Pirko, MatthewKulda, KevinBaylor University.2020-05-202020-05-2020202020-05-20https://hdl.handle.net/2104/10865This paper will examine the intersection of cybersecurity and machine learning. Use cases integrating machine learning for both defensive and offensive cybersecurity will be surveyed. Within defensive cybersecurity, this paper will investigate how machine learning is being used to protect against external threats and internal threats. To show an interesting way machine learning may be used in a cyber attack, this paper will look at a Prime+Probe cache side-channel attack that aims to learn which machine learning transfer model a program is running. From an external perspective, the analysis will show how the side-channel attack may be implemented, and how it can be defended against. Finally, we propose an additional method to detect and prevent this attack on an internal network.en-USBaylor University projects are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission.Machine Learning.Cybersecurity.Transfer Learning.ThesisWorldwide access