Abstract
Automated approaches to cyber security based on machine learning will be necessary to combat the next generation of cyber-attacks. Current machine learning tools, however, are difficult to develop and deploy due to issues such as data availability and high false positive rates. Generative models can help solve data-related issues by creating high quality synthetic data for training and testing. Furthermore, some generative architectures are multipurpose, and when used for tasks such as intrusion detection, can outperform existing classifier models. This paper demonstrates how the future of cyber security stands to benefit from continued research on generative models.
Recommended Citation
Halvorsen, James and Gebremedhin, Dr. Assefaw
(2024)
"Generative Machine Learning for Cyber Security,"
Military Cyber Affairs: Vol. 7
:
Iss.
1
, Article 4.
Available at:
https://digitalcommons.usf.edu/mca/vol7/iss1/4
Included in
Artificial Intelligence and Robotics Commons, Computer and Systems Architecture Commons, Information Security Commons, Software Engineering Commons, Systems Architecture Commons, Systems Science Commons
