Deep learning versus gist descriptors for image-based malware classification
Publication Date
January 2018
Document Type
Contribution to a Book
Publication Title
Proceedings of the 4th International Conference on Information Systems Security and Privacy
Abstract
Image features known as ``gist descriptors'' have recently been applied to the malware classification problem. In this research, we implement, test, and analyze a malware score based on gist descriptors, and verify that the resulting score yields very strong classification results. We also analyze the robustness of this gist-based scoring technique when applied to obfuscated malware, and we perform feature reduction to determine a minimal set of gist features. Then we compare the effectiveness of a deep learning technique to this gist-based approach. While scoring based on gist descriptors is effective, we show that our deep learning technique performs equally well. A potential advantage of the deep learning approach is that there is no need to extract the gist features when training or scoring.
Recommended Citation
Sravani Yajamanam, Vikash Raja Samuel Selvin, Fabio Troia, and Mark Stamp. "Deep learning versus gist descriptors for image-based malware classification" Proceedings of the 4th International Conference on Information Systems Security and Privacy (2018).
