To address the insufficient utilization of traffic characteristics in traditional encrypted traffic classification methods, a multidimensional information image-based encrypted traffic classification method, named MT (multi-dimensional information image encryption traffic classification method), is proposed in this paper. Firstly, traffic data is converted into a specialized traffic image format that incorporates unique information from traffic flow, including packet headers, payloads, and packet length sequences. Then, Transformer architecture is employed to extract global features relevant for classification from traffic images, while the LSTM-FCN(long short-term memory-fully convolutional network) model is utilized to capture both long-range and short-term temporal patterns within the sequential data. Finally, a two-stage fusion classifier is implemented, where the global and temporal features are fed into their respective classifiers to generate two initial decision outcomes. A feature fusion classifier subsequently performs weighted integration of these global and temporal features to produce a third decision. The final prediction is obtained through the fusion of these 3 decision results. Experimental results show that the MT method achieves superior performance across multiple evaluation metrics on both public and self-collected datasets, outperforming all selected baseline methods in the classification task.
MOOREA W, PAPAGIANNAKIK. Toward the accurate identification of network applications[M]//DOVROLIS C.Passive and Active Network Measurement. Berlin, Germany: Springer, 2005:41-54.
DRAPER-GILG, LASHKARIA H, MAMUNM S I, et al. Characterization of encrypted and VPN traffic using time-related features[C]//Proceedings of the 2nd International Conference on Information Systems Security and Privacy. Setúbal, Portugal: SciTePress, 2016:407-414.
[7]
CAIZ Z, JIANGB, LUZ G, et al. IsAnon: flow-based anonymity network traffic identification using extreme gradient boosting[C]//Proceedings of the 2019 International Joint Conference on Neural Networks. Piscataway, USA: IEEE, 2019:1-8.
[8]
LIUC, HEL T, XIONGG, et al. FS-Net: a flow sequence network for encrypted traffic classification[C]//Proceedings of the IEEE INFOCOM 2019—IEEE Conference on Computer Communications. Piscataway,USA: IEEE, 2019:1171-1179.
[9]
LOTFOLLAHIM, JAFARI SIAVOSHANIM, SHIRALI HOSSEIN ZADER, et al. Deep packet: a novel approach for encrypted traffic classification using deep learning[J]. Soft Computing, 2020,24(3):1999-2012.
[10]
LINK D, XUX L, GAOH H. TSCRNN: a novel classification scheme of encrypted traffic based on flow spatiotemporal features for efficient management of IIoT[J]. Computer Networks, 2021,190:No.107974.
[11]
LIUY, WANGX, QUB, et al. ATVITSC: a novel encrypted traffic classification method based on deep learning[J]. IEEE Transactions on Information Forensics and Security, 2024,19:9374-9389.
[12]
LINX J, XIONGG, GOUG P, et al. ET-BERT: a contextualized datagram representation with pre-training transformers for encrypted traffic classification[C]//Proceedings of the ACM Web Conference 2022. New York, USA: ACM, 2022: 633-642.
[13]
WANGQ N, QIANC, LIX C, et al. Lens: a foundation model for network traffic[DB/OL]. (2024-02-06)[2025-11-06].
[14]
ZHAOR J, ZHANM W, DENGX W, et al. Yet another traffic classifier: a masked autoencoder based traffic transformer with multi-level flow representation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2023,37(4):5420-5427.
[15]
DAINOTTIA, PESCAPEA, CLAFFYK C. Issues and future directions in traffic classification[J]. IEEE Network, 2012,26(1):35-40.
[16]
LINP, YEK J, HUY S, et al. A novel multimodal deep learning framework for encrypted traffic classification[J]. IEEE/ACM Transactions on Networking, 2023,31(3):1369-1384.
[17]
HINTONG, VINYALSO, DEANJ. Distilling the knowledge in a neural network[DB/OL]. (2015-03-09)[2025-11-06].
[18]
HABIBI LASHKARIA, DRAPER GILG, MAMUNM S I, et al. Characterization of tor traffic using time based features[C]//Proceedings of the 3rd International Conference on Information Systems Security and Privacy. Setúbal, Portugal: SciTePress, 2017:253-262.
[19]
WANGW, ZHUM, ZENGX W, et al. Malware traffic classification using convolutional neural network for representation learning[C]//Proceedings of the 2017 International Conference on Information Networking. Piscataway, USA: IEEE, 2017:712-717.
[20]
WANGW, ZHUM, WANGJ L, et al. End-to-end encrypted traffic classification with one-dimensional convolution neural networks[C]//Proceedings of the 2017 IEEE International Conference on Intelligence and Security Informatics. Piscataway, USA: IEEE, 2017:43-48.