Deep Learning Techniques for Malware Detection: A Comprehensive Survey
Ajvad Haneef K, S. D. Madhu Kumar · 2023
Malware detection and familial classification approaches based on deep learning (DL) techniques have emerged as a promising solution in recent years. The ability of deep neural networks (DNNs) to learn complex patterns and features from malware samples has resulted in high detection rates and has attracted the attention of researchers in the field of cyber-security. The use of deep learning algorithms in malware detection and familial classification can help to improve the accuracy and efficiency of existing methods and can also be used to detect new and unknown malware variants. DL-based malware detection models are proven to outperform traditional, state-of-the-art machine learning models. Therefore, there exists a greater significance in reviewing existing DL-based malware detection techniques alone. This survey presents a comprehensive overview of state-of-the-art DL techniques used for malware detection. Although there exist few works that review machine learning and deep learning-based malware detection techniques, and to the best of our knowledge, only a limited number of surveys focused on deep learning-based malware detection techniques alone. Overall, this survey provides a comprehensive overview of the recent works in the field that are intended to be a valuable resource for researchers, practitioners, and anyone interested in deep learning-based malware detection. We also present the open issues and challenges in this area which require research attention.