Malware Classification using Diluted Convolutional Neural Network with Fast Gradient Sign Method

TL;DR

This paper introduces FGSM DICNN, a novel malware classification method combining diluted convolutions and fast gradient sign perturbations, achieving high accuracy with fewer features and lower computational costs.

Contribution

It proposes a new malware classification model that uses diluted convolutions and FGSM to improve accuracy and efficiency over existing methods.

Findings

Achieved 99.44% classification accuracy.

Outperformed existing approaches like Custom DNN.

Reduced feature dependence and computational cost.

Abstract

Android malware has become an increasingly critical threat to organizations, society and individuals, posing significant risks to privacy, data security and infrastructure. As malware continues to evolve in terms of complexity and sophistication, the mitigation and detection of these malicious software instances have become more time consuming and challenging particularly due to the requirement of large number of features to identify potential malware. To address these challenges, this research proposes Fast Gradient Sign Method with Diluted Convolutional Neural Network (FGSM DICNN) method for malware classification. DICNN contains diluted convolutions which increases receptive field, enabling the model to capture dispersed malware patterns across long ranges using fewer features without adding parameters. Additionally, the FGSM strategy enhance the accuracy by using one-step perturbations during training that provides more defensive advantage of lower computational cost. This integration helps to manage high classification accuracy while reducing the dependence on extensive feature sets. The proposed FGSM DICNN model attains 99.44% accuracy while outperforming other existing approaches such as Custom Deep Neural Network (DCNN).