CNN in Malware Detection

• Published in: IEEE International Symposium on Computational Intelligence and Informatics pp. 63 - 68
• Main Authors: Dobrovodsky, Patrik, Fleiner, Rita, Kail, Eszter
• Format: Conference Proceeding
• Language: English
• Published: IEEE 19.11.2024
• Subjects: Accuracy; Analytical models; CNN; Convolutional neural networks; Gray-scale; Informatics; Malimg; Malware; malware detection; Systematic literature review; Systematics; Technological innovation
• ISSN: 2471-9269
• DOI: 10.1109/CINTI63048.2024.10830884

This article presents a bibliometric analysis and review of the application of Convolutional Neural Networks (CNNs) in malware detection. Over the past decade, there has been a notable increase in research focused on using CNNs for malware classification, as evidenced by the rising number of publications across different years. This study goes beyond a simple literature review by exploring the progression of malware detection techniques that leverage the conversion of malware binaries into grayscale images, from their inception to current advancements. The review covers the evolution of these methods, detailing key findings and achievements. Furthermore, the article compares the results of various studies, specifically those that tested their models on the widely used Malimg dataset. This comparison highlights the effectiveness of each approach, offering insights into the accuracy and performance trends across different CNN-based malware detection frameworks.