$\mathcal{L}{-}$ ETC: A Lightweight Model Based on Key Bytes Selection for Encrypted Traffic Classification
Jie Cao, Yuwei Xu, Qiao jun Xiang · 2023
To protect the confidentiality of communication data, internet users often use encryption protocols (e.g., TLS/SSL) or tools (e.g., VPN, Tor) for network access. Therefore, as a pivotal network management method, encrypted traffic classification technology is vital for guaranteeing the quality of service, the quality of experience, and network security. Researchers have already developed some end-to-end deep learning-based methods to realize encrypted traffic classification. However, given the constrained computational resources available in real-world network measurement scenarios, the existing approaches with high complexity and computation overhead are not appropriate. In this paper, we propose a lightweight model to tackle this issue. Firstly, we propose a base model based on the self-attention mechanism to obtain the key bytes in packets contributing to the classification. Secondly, we leverage these key bytes to reconstruct the input and then streamline the base model, carrying out a lightweight model, i.e.,$\mathcal{L}{-}$ETC. Finally, we implement experiments on three benchmark datasets.$\mathcal{L}-\mathbf{ETC}^{\prime}\mathrm{s}$macro Fl score of the three tasks exceeds 0.92 with only 0.076M (Million) parameters, and the throughput reaches 917 pps, which is also superior to state-of-the-art methods.