针对目前大多数加密流量分类方法忽略了流量的时序特性和所用模型的效率等问题，提出了一种基于注意力时间卷积网络（attention temporal convolutional network,ATCN）的高效分类方法。该方法首先将流量的内容信息与时序信息共同嵌入模型，增强加密流量的表征；然后利用时间卷积网络并行捕获有效特征以增加训练速度；最后引入注意力机制建立动态特征汇聚，实现模型参数的优化。实验结果表明，该方法在设定的两项分类任务上的性能都优于基准模型，其准确率分别为99.4%和99.8%，且模型参数量最多可降低至基准模型的15%，充分证明了本文方法的先进性。最后，本文在ATCN上引入了一种基于迁移学习的微调方式，为流量分类中零日流量的处理提供了一种新颖的思路。
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.
[1] 潘吴斌, 程光, 郭晓军, 等. 网络加密流量识别研究综述及展望[J]. 通信学报, 2016, 37(9): 154-167. Pan W B, Cheng G, Guo X J, et al. Review and perspective on encrypted traffic identification research [J]. Journal on Communications, 2016, 37(9): 154-167. (in Chinese)
[2] Li R P, Zhao Z F, Zheng J C, et al. The learning and prediction of application-level traffic data in cellular networks [J]. IEEE Transactions on Wireless Communications, 2017, 16(6): 3899-3912.
[3] Aceto G, Ciuonzo D, Montieri A, et al. Multi-classification approaches for classifying mobile app traffic [J]. Journal of Network and Computer Applications, 2018, 103: 131-145.
[4] Rezaei S, Liu X. Deep learning for encrypted traffic classification: an overview [J]. IEEE Communications Magazine, 2019, 57(5): 76-81.
[5] Yang L X, Finamore A, Jun F, et al. Deep learning and zero-day traffic classification: lessons learned from a commercial-grade dataset [J]. IEEE Transactions on Network and Service Management, 2021, 18(4): 4103-4118.
[6] Draper-Gil G, Lashkari A H, Mamun M S I, et al. Characterization of encrypted and vpn traffic using time-related features [C]//2nd International Conference on Information Systems Security and Privacy (ICISSP), 2016: 407-414.
[7] Zheng W P, Zhong J H, Zhang Q Z, et al. MTT: an efficient model for encrypted network traffic classification using multi-task transformer [J]. Applied Intelligence, 2022, 52(9): 10741- 10756.
[8] Wang W, Zhu M, Zeng X W, et al. Malware traffic classification using convolutional neural network for representation learning [C]//International Conference on Information Networking (ICOIN), 2017: 712-717.
[9] 郭帅, 苏旸. 基于数据流的加密流量分类方法[J]. 计算机应用, 2021, 41(5): 1386-1391. Guo S, Su Y. Encrypted traffic classification method based on data stream [J]. Journal of Computer Applications, 2021, 41(5): 1386-1391. (in Chinese)
[10] Wang W, Zhu M, Wang J L, et al. End-to-end encrypted traffic classification with onedimensional convolution neural networks [C]//IEEE International Conference on Intelligence and Security Informatics (ISI), 2017: 43-48.
[11] Yao H P, Liu C, Zhang P Y, et al. Identification of encrypted traffic through attention mechanism based long short term memory [J]. IEEE Transactions on Big Data, 2022, 8(1): 241-252.
[12] 薛文龙, 于炯, 郭志琦, 等. 基于特征融合卷积神经网络的端到端加密流量分类[J]. 计算机工程与应用, 2021, 57(18): 114-121. Xue W L, Yu J, Guo Z Q, et al. End-to-end encrypted traffic classification based on feature fusion convolutional neural network [J]. Computer Engineering and Applications, 2021, 57(18): 114-121. (in Chinese)
[13] Lopez-Martin M, Carro B, Sanchez-Esguevillas A, et al. Network traffic classifier with convolutional and recurrent neural networks for internet of things [J]. IEEE Access, 2017, 5: 18042-18050.
[14] Bai S J, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [DB/OL]. 2018[2023-02-16]. https://arxiv.org/abs/1803.01-271.
[15] Pantiskas L, Verstoep K, Bal H. Interpretable multivariate time series forecasting with temporal attention convolutional neural networks [C]//IEEE Symposium Series on Computational Intelligence (SSCI), 2020: 1687-1694.
[16] Salimans T, Kingma D P. Weight normalization: a simple reparameterization to accelerate training of deep neural networks [C]//30th Conference on Neural Information Processing Systems (NIPS), 2016: 901-909.
[17] Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks [DB/OL]. 2014[2023-2-16]. https://arxiv.org/abs/1409.3215.
[18] 陈海涵, 吴国栋, 李景霞, 等. 基于注意力机制的深度学习推荐研究进展[J]. 计算机工程与科学, 2021, 43(2): 370-380. Chen H H, Wu G D, Li J X, et al. Research advances on deep learning recommendation based on attention mechanism [J]. Computer Engineering & Science, 2021, 43(2): 370-380. (in Chinese)
[19] Xie G R, Li Q, Jiang Y. Self-attentive deep learning method for online traffic classification and its interpretability [J]. Computer Networks, 2021, 196: 108267.
[20] Lotfollahi M, Siavoshani M J, Zade R S H, et al. Deep packet: a novel approach for encrypted traffic classification using deep learning [J]. Soft Computing, 2020, 24(3): 1999-2012.
[21] Zou Z, Ge J G, Zheng H B, et al. Encrypted traffic classification with a convolutional long short-term memory neural network [C]//20th IEEE International Conference on High Performance Computing and Communications (HPCC)/16th IEEE International Conference on Smart City (SmartCity)/4th IEEE International Conference on Data Science and Systems (DSS), 2018: 329-334.
[22] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [DB/OL]. 2017[2023-02-16]. https://arxiv.org/abs/1706.03762.
