Malware Detection with CNNs on Entropy and Greyscale Images

Harry John Darton

Authors

Harry John Darton Sheffield Hallam University https://orcid.org/0009-0004-5674-2609

Keywords:

malware detection, convolutional neural networks, entropy images, greyscale images, static analysis

Abstract

This study investigates whether convolutional neural networks (CNNs) trained on visual representations of Portable Executable (PE) files can rival traditional machine learning classifiers trained on engineered features. A dataset of over 200,000 PE files [1] was used to derive two feature sets (Basic and Ember-Lite) [2] and to generate 256x256 greyscale and entropy images [3],[4]. Three CNNs (SimpleCNN, ResNet-18 [5], EfficientNet-B0 [6]) were trained and evaluated against five baselines (Random Forest, XGBoost [7], CatBoost [8], LightGBM, Logistic Regression). Tree-based models with enriched features achieved the highest scores, with CatBoost reaching a ROC-AUC of 0.990. The best CNN, EfficientNet-B0 on entropy images, obtained a ROC-AUC of 0.954. Although CNNs did not surpass feature-based models, they showed competitive results when feature engineering was constrained. These findings indicate that visual approaches offer a promising alternative for static malware detection, particularly when combined with entropy-based representations [9].

Downloads

Download data is not yet available.

Author Biography

Harry John Darton, Sheffield Hallam University

Harry Darton graduated from Sheffield Hallam University with a first class honours degree in Cyber Security and Digital Forensics. His academic interests centre on digital forensics, incident response, and the application of machine learning techniques to security problems. His final year research focused on static malware detection using image-based convolutional neural networks, where he developed practical skills in Python programming, data engineering, and large-scale model evaluation.

Outside his academic work, he has a long-standing involvement in gaming and competitive esports. He is a former top-100 Overwatch player and competed in the Contenders series as a semi-professional, gaining experience in strategy, teamwork, and operating under pressure. He also enjoys a range of outdoor activities including rock climbing, hiking, and golf, and maintains a strong interest in emerging technologies and personal technical projects. He is now developing his professional portfolio as he prepares for a career in cyber security, with particular interest in threat analysis, digital investigations, and the role of artificial intelligence in defensive security.

References

[1] M. Lester, “PE malware machine learning dataset [Data set],” Practical Security Analytics, 2021. [Online]. Available: https://practicalsecurityanalytics.com/pe-malware-machine-learning-dataset/

[2] H. S. Anderson and P. Roth, “EMBER: An open dataset for training static PE malware machine learning models,” arXiv preprint, 2018. [Online]. Available: https://arxiv.org/abs/1804.04637

[3] L. Nataraj, S. Karthikeyan, G. Jacob, and B. S. Manjunath, “Malware images: Visualization and automatic classification,” in Proc. 8th Int. Symp. Visualization for Cyber Security (VizSec 2011), pp. 1–7, ACM, 2011. doi: 10.1145/2016904.2016908

[4] K. S. Han, J. H. Lim, B. Kang, and E. G. Im, “Malware analysis using visualized images and entropy graphs,” Int. J. Inf. Security, vol. 14, no. 1, p. 1, 2014. doi: 10.1007/s10207-014-0242-0

[5] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR 2016), pp. 770–778, 2016. doi: 10.1109/CVPR.2016.90

[6] M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. 36th Int. Conf. Machine Learning (ICML 2019), vol. 97, pp. 6105–6114, PMLR, 2019. [Online]. Available: https://proceedings.mlr.press/v97/tan19a.html

[7] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD ’16), pp. 785–794, ACM, 2016. doi: 10.1145/2939672.2939785

[8] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: Unbiased boosting with categorical features,” in Proc. 32nd Int. Conf. Neural Information Processing Systems (NeurIPS 2018), pp. 6639–6649, 2018. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2018/hash/14491b756b3a51daac41c24863285549-Abstract.html

[9] A. Bensaoud, N. Abudawaood, and J. Kalita, “Classifying malware images with convolutional neural network models,” arXiv preprint, 2020. [Online]. Available: https://arxiv.org/abs/2010.16108

[10] AV-TEST Institute, “Malware statistics & trends report,” 2024. [Online]. Available: https://www.av-test.org/en/statistics/malware/

[11] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. doi: 10.1038/nature14539

[12] M. Kalash et al., “Malware classification with deep convolutional neural networks,” in Proc. 10th Int. Conf. New Technologies, Mobility and Security (NTMS), pp. 1–5, IEEE, 2018. doi: 10.1109/NTMS.2018.8328749

[13] C. E. Shannon, “A mathematical theory of communication,” Bell Syst. Tech. J., vol. 27, no. 3, pp. 379–423, 1948. doi: 10.1002/j.1538-7305.1948.tb01338.x

[14] M. Brosolo and M. Conti, “The road less travelled: Investigating robustness and explainability in CNN malware detection,” arXiv preprint, 2025. doi: 10.48550/arXiv.2503.01391

[15] B. Al-Masri, N. Bakir, A. El-Zaart, and K. Samrouth, “Dual convolutional malware network (DCMN): An image-based malware classification using dual convolutional neural networks,” Electronics, vol. 13, no. 18, p. 3607, 2024. doi: 10.3390/electronics13183607

[16] J. Saxe and K. Berlin, “Deep neural network based malware detection using two-dimensional binary program features,” arXiv preprint arXiv:1508.03096, 2015.

[17] E. Raff et al., “Malware detection by eating a whole EXE,” arXiv preprint arXiv:1710.09435, 2017.