Semantic Malware Classification Using Artificial Intelligence Techniques

Abstract

The growing threat of malware, particularly in the Portable Executable (PE) format, demands more effective methods for detection and classification. Machine learning-based approaches exhibit their potential but often neglect semantic segmentation of malware files that can improve classification performance. This research applies deep learning to malware detection, using Convolutional Neural Network (CNN) architectures adapted to work with semantically extracted data to classify malware into malware families. Starting from the Malconv model, this study introduces modifications to adapt it to multi-classification tasks and improve its performance. It proposes a new innovative method that focuses on byte extraction from Portable Executable (PE) malware files based on their semantic location, resulting in higher accuracy in malware classification than traditional methods using full-byte sequences. This novel approach evaluates the importance of each semantic segment to improve classification accuracy. The results revealed that the header segment of PE files provides the most valuable information for malware identification, outperforming the other sections, and achieving an average classification accuracy of 99.54%. The above reaffirms the effectiveness of the semantic segmentation approach and highlights the critical role header data plays in improving malware detection and classification accuracy.