Unsupervised Feature Learning Methodology for Tree Based Classifier and SVM to Classify Encrypted Traffic

Presently, sample social applications have emerged, and each one is trying to knock down the other. They expand their game by bringing novelty to the market, being ingenious and providing advanced level of security in the form of encryption. It has become significant to manage the network traffic and analyze it; hence we are performing a network traffic binary classification on one of the globally used application - WhatsApp. Also, this will be helpful to evaluate the sender-receiver system of the appli-cation alongside stipulate the properties of the network traces. By analyzing the behavior of network traces, we can scrutinize the type and nature of traffic for future maintenance of the network. In this study, we have carried out three different objectives. First, we have classified between the WhatsApp network packets and other applications using different ML classifiers, secondly, we have segmented the WhatsApp application files into image and text and third, we have incorporated a deep learning module with the same ML classifiers to understand and boost the performance of the previous experiments. Following the experiments, we have also highlighted the difference in the performance of both tree -based and vector-based classifiers of Machine Learning. Based on our findings, XGBoost classifier is a pre-eminent algorithm in the identification of WhatsApp network traces from the dataset. Whereas in the experiment of WhatsApp media segmentation, Random Forest has outperformed the other ML algorithms. Similarly, SVM when clubbed with a Deep Learning Auto encoder boosts the performance of this vector-based classifier in the binary classification task.