Enhancing Malware Detection and Classification through Hybrid Deep Learning Architectures: A Comparative Analysis of CNNs and RNNs

Abstract

The increasing sophistication of malware poses significant challenges to traditional detection methods. This paper investigates the effectiveness of hybrid deep learning architectures that combine Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for malware detection and classification. Through comparative analyses, we evaluate the performance of these hybrid models against standalone CNNs and RNNs using benchmark datasets. Results indicate that the hybrid approach not only enhances detection accuracy but also improves the model's ability to generalize across various malware families.