A natural language-inspired multilabel video streaming source identification method based on deep neural networks

Existing website fingerprinting techniques are not effective with video streaming traffic when the encrypted traffic contains multiple streams. This paper presents a deep learning-based source identification method for identifying multiple video sources within a single encrypted tunnel. The core contribution is a novel feature inspired by natural language processing (NLP) that allows existing NLP techniques to identify the source. The feature extraction method is described. A large dataset containing video streaming and web traffic is created to verify its effectiveness. Results are obtained by applying several NLP methods to show that the proposed method performs well on both binary and multilabel traffic classification problems. The work proves that the method can overcome the challenges given by mixed-traffic tunnels.