Malware Detection Using Deep Learning

No Thumbnail Available
Authors
Parkar, Saifallah Liyaqat
Issue Date
2024
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights
Abstract
Several models were implemented and evaluated in this work on deep learning-based malware detection. These models comprised Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Graph Sample and Aggregated (GraphSAGE), Graph Convolutional Network (GCN), Hyper-parameter GCN, Graph Isomorphism Network, and Graph Attention Network. The Graph Isomorphism Network has the highest accuracy (97.58%), while the other models also had varied degrees of accuracy. The paper promotes cybersecurity by providing a comparative analysis of multiple deep-learning models for malware detection. The outcomes of this study may affect the development of more reliable and accurate malware detection systems. These findings indicate the promise of specialized graph-based neural networks, particularly Graph Isomorphism Networks. This work increases our understanding of deep learning applications in cybersecurity and stresses the need to select appropriate models for certain tasks, paving the way for more powerful malware detection tools.