Deep Graph Neural Networks for Malware Detection Using Ghidra P-Code

Authors

  • Rinaldo Iorizzo Rochester Institute of Technology
  • Bo Yuan Rochester Institute of Technology

DOI:

https://doi.org/10.34190/eccws.23.1.2344

Keywords:

Malware detection, Deep Learning, Artificial Intelligence, Ghidra, Graph Neural Network

Abstract

This work examines the effectiveness of using Ghidra P-Code as semantics-based features in a graph neural network-based malware detection system. A preliminary model exhibits a function level precision of ∼70% and a recall around ∼60%, and a precision and recall of ~55% and ~80% respectively for the program level detection task on a dataset of ∼50,000 control flow graphs extracted from functions of malicious and benign programs. Future improvements to this ongoing project include, but are not limited to, collecting dynamic control flow graph information as opposed to static graphs to provide the model with resilience to advanced malware obfuscation and encryption schemes.

Author Biographies

Rinaldo Iorizzo, Rochester Institute of Technology

Rinaldo Iorizzo is a PhD student in the GCCIS program at the Rochester Institute of technology. His primary area of research is malware detection using deep lerning techinques. He obtained a Bachelor of Science in Computer Science from SUNY Oswego. He is a receipant of the NSF CyberCorps Scholarship. 

Bo Yuan, Rochester Institute of Technology

Bo Yuan is a professor in the Cybersecurity Department at Rochester Institute of Technology. He was the department chair from 2014 to 2022 and oversaw the tremendous growth of the department and the cybersecurity programs. His research areas are computational intelligence and its application in cybersecurity. Dr. Yuan is the PI of multiple cybersecurity grants, including the CyberCorps (R) Scholarship for Service grant funded by the National Science Foundation (NSF) and the DoD Cyber Scholarship Program. He is the POC of CAE-CD and CAE-R at RIT. Before he joined RIT in 2003, Dr. Yuan was a staff scientist at Manning & Napier Information Services. He received a Ph.D. in Systems Science from Binghamton University in 1996.

Downloads

Published

2024-06-21