Abstract: Aiming at the problem that most current encrypted traffic classification methods ignore the timing characteristics in the traffic and the model efficiency, we propose an efficient classification method based on attention temporal convolutional network (ATCN). This method first embeds content information and timing information into the model to enhance the representation of encrypted traffic. Then it utilizes temporal convolutional network to capture effective features in parallel to increase training speed. Finally, we introduce attention mechanism to establish dynamic feature aggregation to optimize model parameters. Experimental results show the superior performance of our proposed method over the baseline in two classification tasks, achieving accuracy of 99.4% and 99.8%, respectively, while reducing the number of model parameters to a maximum of 15% of the baseline. Finally, a fine-tuning method based on transfer learning is introduced to the ATCN, which provides a novel approach for zero-day traffic processing in traffic classification.

Key words: encrypted traffic classification, temporal convolutional network (TCN), attention mechanism, transfer learning