Search

BiGRU-DA-BERT Encrypted Traffic Classification Technology Based on BERT

Author(s)

Haobo Liang*, Yingxiong Leng, Jinman Luo, Jie Chen, Xiaoji Guo

Affiliation(s)

Dongguan Power Supply Bureau, Guangdong Power Grid Corporation, Dongguan, Guangdong, China

Abstract

Compared with traditional models and methods, pre-trained models have been gradually applied to the field of network encrypted traffic classification in recent years due to automatic feature learning, strong generalization ability and dynamic adaptability. The weight of minority categories of data is increased, and the Focal Loss function is introduced to further increase the focus on minority categories. Experimental results show that the improved model improves the overall classification accuracy by 2.3% and the average F1 value of minority classes by 15.3% on the dataset, which proves the effectiveness of model architecture optimization and adjustment model classification, and also provides a new way to improve the classification accuracy of minority categories in unbalanced datasets.

Keywords

Encrypted Traffic Classification; BERT; BiGRU; Differential Attention Mechanism

References

[1]X. Wang, "FDGM: A Lightweight Model for Privacy-Preserving Encrypted Traffic Classification," IEEE Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China, 2025, pp. 686-691, doi: 10.1109/ITOEC63606.2025.10967753. [2]J. Kotak, I. Yankelev, I. Bibi, Y. Elovici and A. Shabtai, "VPN-Encrypted Network Traffic Classification Using a Time-Series Approach," in IEEE Transactions on Network and Service Management, vol. 22, no. 2, pp. 2225-2242, April 2025, doi: 10.1109/TNSM.2025.3543903. [3]Z. Chen, G. Cheng, Z. Wei, D. Niu and N. Fu, "Classify Traffic Rather Than Flow: Versatile Multi-Flow Encrypted Traffic Classification With Flow Clustering," in IEEE Transactions on Network and Service Management, vol. 21, no. 2, pp. 1446-1466, April 2024, doi: 10.1109/TNSM.2023.3322861. [4]G. Lv, R. Yang, Y. Wang and Z. Tang, "Network Encrypted Traffic Classification Based on Secondary Voting Enhanced Random Forest," 2020 IEEE 3rd International Conference on Computer and Communication Engineering Technology (CCET), Beijing, China, 2020, pp. 60-66, doi: 10.1109/CCET50901.2020.9213165. [5]Wang W, Zhu M, Wang J, et al. End-to-end encrypted traffic classification with one dimensional convolution neural networks//2017 IEEE international conference on intelligence and security informatics (ISI). IEEE, 2017: 43-48. [6]Lotfollahi M, Siavoshani M J, Zade R S H, et al. Deep packet: A novel approach for encrypted traffic classification using deep learning. Soft Computing, 2020, 24(3):1999-2012. [7]Y. Liu, X. Wang, B. Qu and F. Zhao, "ATVITSC: A Novel Encrypted Traffic Classification Method Based on Deep Learning," in IEEE Transactions on Information Forensics and Security, vol. 19, pp. 9374-9389, 2024, doi: 10.1109/TIFS.2024.3433446. [8]N. Malekghaini. "AutoML4ETC: Automated Neural Architecture Search for Real-World Encrypted Traffic Classification," in IEEE Transactions on Network and Service Management, vol. 21, no. 3, pp. 2715-2730, June 2024, doi: 10.1109/TNSM.2023.3324936. [9]Cinar Y G, Mirisaee H, Goswami P, et al. Period-aware content attention RNNs for time series forecasting with missing values. Neurocomputing, 2018, 312: 177-186. [10]Rezaei S, Liu X. Deep learning for encrypted traffic classification: An overview. IEEE communications magazine, 2019, 57(5): 76-81. [11]Papadogiannaki E, Ioannidis S. A survey on encrypted network traffic analysis applications, techniques, and countermeasures. ACM Computing Surveys (CSUR), 2021, 54(6): 1-35. [12]Salman O, Elhajj I H, Kayssi A, et al. A review on machine learning–based approaches for Internet traffic classification. Annals of Telecommunications, 2020, 75(11): 673-710. [13]Lin P, Ye K, Hu Y, et al. A novel multimodal deep learning framework for encrypted traffic classification. IEEE/ACM Transactions on Networking, 2022, 31(3): 1369-1384. [14]Li R, Xiao X, Ni S, et al. Byte segment neural network for network traffic classification//2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS). IEEE, 2018: 1-10. [15]S. Cui. "FG-SAT: Efficient Flow Graph for Encrypted Traffic Classification Under Environment Shifts," in IEEE Transactions on Information Forensics and Security, vol. 20, pp. 5326-5339, 2025, doi: 10.1109/TIFS.2025.3571663.