In this study, we investigate using deep learning, i.e., deep convolutional neural networks (DCNNs), for malware detection leveraging network traffic data. Signature-based detection techniques are now proven unable to cope with the extremely high rate of malware variants' evolution. For this reason, this research suggests a novel method of turning raw network traffic data input (APKS, CSVS, and PCAPS) into visual representations for better malware classification. The study trains a model using DCNNs and refines it using the VGG19 architecture and extra convolutional layers to achieve higher detection rates utilizing the CICAndMal2017 dataset. The key metrics of precision (98.5%), recall (99.4%), and F1 score (98.8%) are all observed with a high performance, along with the AUC of 0.93 and accuracy rate of 99.35%. Deep learning is demonstrated to be effective in detecting malware via image-based features, and there is a significant improvement compared to traditional approaches. The novelty in this work is the use of deep learning for malware detection via visual representations of network traffic. Future work will improve computational efficiency, extend the approach to dynamic environments, and learn to be more robust to evasion tactics through adversarial training.
Otoom et al. (Sun,) studied this question.