Zenith: Real-time Identification of DASH Encrypted Video Traffic with Distortion

Weitao Tang, Jianqiang Li, Meijie Du, Die Hu, Qingyun Liu

Abstract: Some video traffic carries harmful content, such as hate speech and child abuse, primarily encrypted and transmitted through Dynamic Adaptive Streaming over HTTP (DASH). Promptly identifying and intercepting traffic of harmful videos is crucial in network regulation. However, QUIC is becoming another DASH transport protocol in addition to TCP. On the other hand, complex network environments and diverse playback modes lead to significant distortions in traffic. The issues above have not been effectively addressed. This paper proposes a real-time identification method for DASH encrypted video traffic with distortion, named Zenith. We extract stable video segment sequences under various itags as video fingerprints to tackle resolution changes and propose a method of traffic fingerprint extraction under QUIC and VPN. Subsequently, simulating the sequence matching problem as a natural language problem, we propose Traffic Language Model (TLM), which can effectively address video data loss and retransmission. Finally, we propose a frequency dictionary to accelerate Zenith's speed further. Zenith significantly improves accuracy and speed compared to other SOTA methods in various complex scenarios, especially in QUIC, VPN, automatic resolution, and low bandwidth. Zenith requires traffic for just half a minute of video content to achieve precise identification, demonstrating its real-time effectiveness. The project page is available at https://anonymous.4open.science/r/Zenith-Anonymous.

Primary Subject Area: [Systems] Transport and Delivery

Secondary Subject Area: [Systems] Systems and Middleware, [Systems] Data Systems Management and Indexing, [Experience] Interactions and Quality of Experience

Relevance To Conference: Our work holds significant importance in multimedia security. Our work ensures the timely regulation and interception of video traffic carrying harmful content such as hate speech and child abuse, thereby protecting video users, especially vulnerable groups such as children and adolescents, both physically and mentally. It enables real-time identification of DASH encrypted video traffic to determine whether it belongs to harmful videos. In contrast to other works on encrypted video traffic identification, our work addresses various distortions in traffic to enable practical application. It can identify TLS and QUIC encrypted video traffic transmitted under DASH in real-time, even in complex network environments and playback modes such as low bandwidth, VPN, and automatic resolution. With traffic for just half a minute of video content, our work achieves an identification accuracy of 97.32%, demonstrating its efficient applicability in natural network environments. Currently, no existing encrypted video traffic identification methods match our effectiveness. Finally, we contribute our project source code and data.

Submission Number: 1535