Intelligent malware classification based on network traffic and data augmentation techniques

To prevent detection, attackers frequently design systems to rearrange and rewrite their malware automatically. The majority of machine learning techniques are not sufficiently resistant such re-orderings because they develop a classifier based on manually created feature vector. Deep like convolutional neural networks (CNN) have lately proven perform better than more traditional algorithms, especially in applications picture categorization. As result this success, CNN network proposed with data augmentation (to enhance the performance) classify samples. We trained photos using converted grayscale images from files. Our methodology outperforms other methods an accuracy 98.80%, according experimental results.