| A Survey on Cybersecurity Enhancing Malware Classification using Deep Learning Convolution Neural Networks |
| Paper ID : 1125-ICEEM2023 (R1) |
| Authors: |
|
Ahmed Hawana * Department of Electronics and Electrical Communications Engineering
Faculty of Electronic Engineering, Menoufia University
Menoufia University, Menouf 32952, Egypt |
| Abstract: |
| Malware poses a persistent and evolving threat to cybersecurity including computer systems and networks, necessitating the development of robust classification methods for timely detection and mitigation. Deep Learning Convolutional Neural Networks (CNNs) have revealed outstanding capabilities in image recognition, motivating researchers to explore their applicability in malware classification by converting binary files into grayscale images. This paper offers valuable insights into the current state of malware classification using CNN models research to enhance categorization process from different attitudes. Latest research competed to boost the classification performance by using various CNN techniques by which we could see that accuracy ranged from 93.2% for the method that used a simple convolution filter to 99.97% for the method that used multi convolution layers with 100 epochs and that used fine tuning Transfer Learning TL. The work underscores the significance of deep learning techniques, particularly CNNs, in advancing cybersecurity efforts and identifies avenues for future research to further enhance the accuracy and robustness of malware detection systems. |
| Keywords: |
| CNN, Deep Learning, malware, classification, Machine Learning, Transfer Learning, Cybersecurity |
| Status : Paper Accepted |
