Publication Date

Spring 2015

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Mark Stamp

Second Advisor

Jon Pearce

Third Advisor

Fabio Di Troia


support vector machines metamorphic malware detection


Metamorphic malware changes its internal structure with each infection, which makes it challenging to detect. In this research, we test several scor- ing techniques that have shown promise in metamorphic detection. We then perform a careful robustness analysis by employing morphing strategies that cause each score to fail. Finally, we show that combining scores using a Sup- port Vector Machine (SVM) yields results that are significantly more robust than we obtained using any of the individual scores.