A CNN Based Encrypted Network Traffic Classifier
Zulu Okonkwo, Ernest Foo, Qinyi Li, Zhé Hóu
Abstract
Internet encryption ensures security by improving privacy between sender and receiver. The unstructured form of encrypted data creates a problem of poor traffic classification for security systems. Recent developments using Artificial Intelligence to address this problem left issues like model simplicity, complexity, imbalanced dataset etc, unaddressed. Overfitting, underfitting and ultimately poor classification are outcomes of poorly designed models. This paper applies deep learning to the problem of traffic classification. An eleven layered Convolutional Neural Network (CNN) is designed and trained with a range of images generated from the metadata of encrypted traffic. At its core, the design is simple and deals with overfitting. The proposed model is assessed with the standard metrics, accuracy, precision, recall and score, then compared to a baseline model. The model is trained and tested for seven classification problems, using three encryption types (https, vpn, tor). For all classification tasks, the model achieved accuracies ranging from 91% - 99%, which is an indication of optimum generalization strength. Our model outperformed the baseline model which had accuracies ranging from 67.6% - 99%, an indication of poor generalization strength.