Deep Learning Techniques for Malware Detection

EasyChair Preprint 14337

Abstract

In recent years, the proliferation of cyber threats has necessitated the development of and heuristic approaches, struggle to keep pace with the evolving nature of malware. Deep learning techniques have emerged as a promising solution to address these challenges. This paper provides a comprehensive review of deep learning methods applied to malware detection. We examine various architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and their hybrid variants, focusing on their ability to identify and classify malicious software with high accuracy. The paper also discusses the integration of deep learning models with feature extraction techniques, such as static and dynamic analysis, to enhance detection performance. We highlight key advancements, including transfer learning and ensemble methods, and address challenges such as model interpretability and computational efficiency. Finally, we present a comparative analysis of recent studies, providing insights into the effectiveness and limitations of current approaches. This review aims to guide future research directions and foster the development of more sophisticated malware detection systems.

Keyphrases: Cyber Security, learning, machine

@booklet{EasyChair:14337,
  author    = {Obaloluwa Ogundairo and Peter Broklyn},
  title     = {Deep Learning Techniques for Malware Detection},
  howpublished = {EasyChair Preprint 14337},
  year      = {EasyChair, 2024}}