Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Mark Stamp
Second Advisor
Katerina Potika
Third Advisor
William B. Andreopoulos
Keywords
Malware, Support Vector Machine, Long Short-Term Memory, Convolutional Neural Network, Portable Executable file
Abstract
The threat of malware has remained a serious concern for computer networks and systems, highlighting the need for accurate classification techniques. This research adopted the structured nature of PE files incorporated with a multi-modal machinelearning approach, to classify malware types. Features extracted from the PE headers were used to train an LSTM model. Features extracted from the PE sections were used to train a CNN model. Probabilities produced from these two models were then concatenated and fed into an SVM classifier. This multi-modal approach demonstrated high accuracy by experimenting with and verifying the approach on a large and labeled dataset. This research compared the results of the multi-modal approach with those of different preliminary models, including SVM, LSTM, and CNN. The proposed approach showed meaningful improvement in malware classification, demonstrating the potential of a multi-modal approach for accurate malware detection.
Recommended Citation
Jiang, Jonathan, "Multimodal Techniques for Malware Classification" (2024). Master's Projects. 1448.
https://scholarworks.sjsu.edu/etd_projects/1448
