Article Details

Title · Authors · Abstract · Keywords · DOI · References

Optimization and Evaluation of Cross-scenario Encrypted Traffic Classification and Malicious Attack Detection Models

JIANG Yifei

(China University of Political Science and Law, Beijing 100088, China)

Section：Network and Information Security · Vol. 2026, Issue 12 · Pages：164-171 · 2096-4706（2026）12-0164-08 · CLC number：TP393.08 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.12.031

Abstract

By systematically reviewing the application scenarios and challenges of network traffic classification, as well as recent research advancements in this field, the paper focuses on analyzing the development of classification models and the evaluation processes for traffic classification. It aims to summarize current research progress and provide direction for innovation in traffic classification technology. In recent years, traffic classification models are mainly based on Machine Learning and Deep Learning algorithms to achieve traffic classification. The evaluation process employs metrics such as accuracy, stability, robustness, and resource consumption to construct a multidimensional assessment system. Research indicates that existing methods achieve significant progress in mitigating sample imbalance, alleviating label scarcity, and enhancing feature extraction. However, issues such as limited datasets, insufficient protocol identification granularity, and difficulty in balancing classification efficiency and precision persist. Future research needs to continuously address these issues, focusing on cross-scenario transfer learning and lightweight model design to push network traffic classification technology toward a more intelligent and adaptive direction.

Keywords

network traffic classification; encrypted traffic; malicious traffic; anonymous traffic; IoT; online game traffic

References

  1. [1] Aleisa M A. Traffic Classification in SDN-based IoT Network Using Two-level Fused Network with Self-adaptive Manta Ray Foraging [J].Scientific Reports，2025，15（1）：881.
  2. [2] Guo Li, Sun Hua Traffic classification method for power data communication network based on K-means and support vector machine SVM [J]. Network Security Technology and Application, 2024 (4): 64-66
  3. [3] Meng Zhaona, Li Yajun, Li Shang, etc Application classification of power communication network based on traffic classification technology [C]//The 14th Academic Conference of the Power Communication Professional Committee of the Chinese Society of Electrical Engineering, 2024: 242-247
  4. [4] Wang Cong, Zheng Haijie, Huang Zhen, etc Traffic classification of power Internet of Things based on self attention hybrid model [J]. Shandong Electric Power Technology, 2025, 52 (6): 62-74
  5. [5] Tuyishime E，Martalò M，Cotfas P A，et al. Resource-efficient Traffic Classification Using Feature Selection for Message Queuing Telemetry Transport-Internet of Things Network-Based Security Attacks [J/OL].Applied Sciences，2025，15（8）：4252.https://doi.org/10.3390/app15084252
  6. [6] Xiong Y Y，Dong S L，Liu R T，et al. IoT Network Traffic Classification: A Deep Learning Method with Fourier Transform-assisted Hyperparameter Optimization [J/OL].Frontiers in Physics，2023，11.https://doi.org/10.3389/fphy.2023.1273862.
  7. [7] Zarzoor A R，Al-Jamali N A S，Al-Saedi I R K. Traffic Classification of IoT Devices by Utilizing Spike Neural Network Learning Approach [J].Mathematical Modelling of Engineering Problems，2023，10（2）：639-646.
  8. [8] Mo Dingtao, Ju Ying, Li Wenjin, etc Research on Traffic Classification Methods for Satellite Networks [J]. Computer Engineering, 2025, 51 (5): 9-19
  9. [9] Wang Guangming, Li Dongqing, Jiang Congfeng Anomaly detection of network traffic in data centers under imbalanced datasets [J]. Computer Engineering, 2025, 51 (8): 227-237
  10. [10] Ning Anan, Nian Mei, Zhang Jun Network game traffic recognition based on PCA and multi class SVM [J]. Computer and Digital Engineering, 2024, 52 (9): 2739-2744
  11. [11] Ning Anan, Zhang Jun, Nian Mei Network game traffic classification based on autoencoder [J]. Computer System Applications, 2023, 32 (7): 113-120
  12. [12] Tang Yan, Wang Heng, Ma Ziqiang, etc Research on Tor Traffic Classification Based on Improved Bidirectional Memory Residual Network [J]. Information Security Research, 2025, 11 (5): 447-456
  13. [13] Cui Youwen, Feng Qianye, He Yunhua, etc Research on Encryption Traffic Analysis Based on Federated Learning [J]. Network Security and Data Governance, 2025, 44 (1): 9-14, 36
  14. [14] Yu Xiaowei, Chen Danwei Research on Graph Neural Network Encryption Traffic Classification Based on Attention Mechanism [J]. Information Security Research, 2023, 9 (1): 13-21
  15. [15] Dornala S K，Senthilkumar P. Real-Time Threat Identification and Categorization in Network Traffic Using Deep Learning Behavioral Analysis [J/OL].International Journal on Smart Sensing and Intelligent Systems，2025，18（1）：20250017.https://reference-global.com/article/10.2478/ijssis-2025-0017.
  16. [16] Ehmer J，Savaria Y，Granado B，et al. Network Attack Classification with a Shallow Neural Network for Internet and Internet of Things (IoT) Traffic [J/OL].Electronics，2024，13（16）：3318.https://doi.org/10.3390/electronics13163318.
  17. [17] Wang Haikuan Traffic detection of CTU-13 botnet based on XGBoost [J]. Journal of Xi'an University of Arts and Sciences (Natural Science Edition), 2023, 26 (4): 27-34
  18. [18] Chen Ziao, Chen Junqiang Design and Implementation of Router Attack Defense Based on Interface Protocol [J]. Network New Media Technology, 2023, 12 (5): 27-32
  19. [19] Wu Yonghui, Yang Weilin, Du Zhonghui, etc Similar traffic strategies to resist website fingerprint attacks [J]. Software Guide, 2023, 22 (8): 172-177
  20. [20] Xu Chengcheng, Zhai Jiangtao, Liu Guangjie, etc A hierarchical classification method for typical anonymous network traffic [J]. Computer Applications and Software, 2025, 42 (7): 132-139211
  21. [21] Zhao Xiaolin, Wang Qiyao, Zhao Bin, etc Research on anonymous traffic classification method based on machine learning [J]. Information Network Security, 2023, 23 (5): 1-10
  22. Liu Taotao, Fu Yu, Yu Yihan, etc Encryption traffic classification method based on parallel traffic graph and graph neural network [J]. Journal of Communications, 2025, 46 (6): 45-59
  23. [23] Chen Tuo, Shi Hao, Li Xiangjie, etc Encryption Traffic Classification Method Based on Spatiotemporal Feature Adaptive Fusion Network [J]. Journal of Central South University for Nationalities (Natural Science Edition), 2024, 43 (3): 384-392
  24. [24] Zhong Hailong, He Yueshun, He Linlin, etc Classification of encrypted traffic based on cost sensitive convolutional neural networks [J]. Computer and Modernization, 2024 (5): 55-60
  25. Geng Haijun, Dong Yun, Hu Zhiguo, etc Encryption Traffic Classification Method Based on Attention 1 DCNN-CE [J]. Computer Applications, 2025, 45 (3): 872-882
  26. [26] Zhang Mengmeng, Nian Mei, Zhang Jun A method for identifying encrypted application traffic based on sample augmentation [J]. Computer and Digital Engineering, 2023, 51 (11): 2638-2642
  27. [27] Li Rui, Ding Yaojun Encryption Traffic Classification Method Based on Attention GAN [J]. Communication Technology, 2023, 56 (2): 175-182
  28. [28] Park J-T，Shin C-Y，Baek U-J，et al. Fast and Accurate Multi-task Learning for Encrypted Network Traffic Classification [J/OL].Applied Sciences，2024，14（7）：3073.https://doi.org/10.3390/app14073073.
  29. Feng Shuwen, Li Yuheng, Bai Xuyang PTNet: A Semi Supervised Parallel Transformer Network for Encryption Traffic Classification [J]. Telemetry and Remote Control, 2024, 45 (3): 43-51
  30. [30] Huaman, Wang Zhao, Zhuang Jianxun Malicious encrypted traffic detection method based on data classification [J]. Information Security and Communication Confidentiality, 2025 (1): 67-77
  31. [31] Zhang Fei, Han Bin, Zhang Fan Encryption traffic classification based on self attention convolutional neural network [J]. Electronic Design Engineering, 2025, 33 (6): 149-154
  32. Wu Jiulian, Ji Xiangmin Classification of encrypted traffic based on SCConv-BiMamba2 [J]. Journal of Beijing University of Information Science and Technology (Natural Science Edition), 2025, 40 (2): 66-73
  33. Hu Guangwu, Jia Ruchun, Xiao Xi A decentralized application encrypted traffic classification model based on neural networks [J]. Journal of Weapon Equipment Engineering, 2025, 46 (6): 234-242
  34. [34] Cui Yongjun, Hao Lixin Encryption traffic classification method based on parallel fusion model [J]. Electronic Design Engineering, 2024, 32 (2): 41-45
  35. [35] Wang Xi, Zhu Chenlu, Zhang Tian Classification of encrypted network traffic based on convolutional neural networks [J]. Computer programming skills and maintenance, 2024 (2): 163-165
  36. [36] Kang Jianhao, Ling Jie Encryption Traffic Classification Method Based on Dense Connected Convolutional Networks [J]. Computer Applications and Software, 2024, 41 (9): 363-369
  37. [37] Sun Yi, Gao Jian, Gu Yijun Malicious encrypted traffic detection by integrating one-dimensional Inception structure and ViT [J]. Computer Engineering, 2023, 49 (1): 154-162
  38. [38] Cui J，Bai L K，Zhang X F，et al. The Attention-based Autoencoder for Network Traffic Classification with Interpretable Feature Representation [J/OL].Symmetry，2024，16（5）：589.https://doi.org/10.3390/sym16050589.
  39. [39] Wang C，Zhang W，Hao H，et al. Network Traffic Classification Model Based on Spatio-temporal Feature Extraction [J/OL].Electronics，2024，13（7）：1236.https://doi.org/10.3390/electronics13071236.
  40. Chen Ruilong, Yi Peng, Hu Tao, etc Encryption traffic classification method based on federated prototype incremental learning [J]. Computer Applications, 2025, 45 (12): 3888-3895
  41. [41] Jin Z P，Duan K，Chen C H，et al. FedETC: Encrypted Traffic Classification Based on Federated Learning [J/OL].Heliyon，2024，10（16）：e35962.https://pmc.ncbi.nlm.nih.gov/articles/PMC11367454/.
  42. [42] Duan X Y，Fu Y，Wang K. Network Traffic Anomaly Detection Method Based on Multi-scale Residual Classifier [J].Computer Communications，2023，198（1）：206-216.
  43. [43] Fang Huiting Research on Identifying Abnormal Behavior of Large scale Network Attack Traffic under the Background of Network Security [J]. Information Research, 2025, 51 (4): 54-62, 68
  44. [44] Huang Pengyu Research on the Application of Deep Neural Networks in Network Traffic Classification and Anomaly Detection [C]//The 5th Academic Exchange Conference on Engineering Technology Management and Digital Transformation, 2025:23-25
  45. [45] Lu Haotian, Dong Yuning, Quan Yuxuan A method for continuous detection and classification of malicious network flows based on a two-layer model and indicator distribution [J]. Acta Sinica, 2025, 53 (5): 1637-1649
  46. [46] Wang Yifeng, Guo Yuanbo, Chen Qingli, etc A fine-grained malicious traffic classification method based on contrastive incremental learning [J]. Journal of Communications, 2023, 44 (3): 1-11
  47. Lin Tongcan, Ge Wenhan, Wang Junfeng Small sample abnormal traffic classification based on aligned prototype network [J]. Journal of Sichuan University (Natural Science Edition), 2024, 61 (3): 9-20
  48. [48] Du Wenyong, Xu Liyang, Wang Chenfei, etc Flow anomaly detection method based on fusion flow energy model [J]. Computer Engineering and Applications, 2024, 60 (20): 274-283
  49. [49] Du W M，Liang D，Lyu Y Q，et al. Group & Reweight: A Novel Cost-sensitive Approach to Mitigating Class Imbalance in Network Traffic Classification [J].International Journal of Machine Learning and Cybernetics，2025，16（10）：7707-7728.
  50. [50] Alrayes F S，Zakariah M，Driss M，et al. Deep Neural Decision Forest (DNDF): A Novel Approach for Enhancing Intrusion Detection Systems in Network Traffic Analysis [J/OL].Sensors，2023，23（20）：8362.https://doi.org/10.3390/s23208362.
  51. Ding Ruiyang, Sun Lei, Dai Leyu, etc A general perturbation based adversarial network traffic generation method [J]. Computer Science, 2025, 52 (2): 336-343
  52. [52] Zhang Guomin, Tu Zhixin, Xing Changyou, etc Traffic Time Series Feature Confusion Method Based on Adversarial Samples [J]. Information Network Security, 2024, 24 (12): 1882-1895
  53. [53] Wang Zhengwen, Wang Junfeng Unknown malicious traffic classification method based on generative zero sample learning [J]. Journal of Sichuan University (Natural Science Edition), 2023, 60 (4): 73-80
  54. [54] Naseer M，Ullah F，Ijaz S，et al. Obfuscated Malware Detection and Classification in Network Traffic Leveraging Hybrid Large Language Models and Synthetic Data [J/OL].Sensors，2025，25（1）：202.https://doi.org/10.3390/s25010202.
  55. [55] Yu Changhong, Lu Ya, Wang Haixin, etc IoT device traffic classification algorithm based on sliding time window [J]. Computer Engineering, 2023, 49 (7): 259-268
  56. Hu Zhongze, Qin Hongchao, Li Zhenjun, etc TCGCL: A Complex Network Traffic Classification Algorithm Based on Graph Contrastive Learning [J]. Computer Science and Exploration, 2025, 19 (5): 1230-1240
  57. [57] Salau A O，Beyene M M. Software Defined Networking Based Network Traffic Classification Using Machine Learning Techniques [J/OL].Scientific Reports，2024，14（1）：20060.https://www.nature.com/articles/s41598-024-70983-6.
  58. Jin Yanliang, Chen Yantao, Gao Yuan, etc Encryption traffic classification based on attention time convolutional network [J]. Chinese Journal of Applied Sciences, 2024, 42 (4): 659-672
  59. Yun Bensheng, Gan Xiaoya, Qian Yaguan A network traffic classification method based on random forest and improved convolutional neural network [J]. Telecommunication Science, 2023, 39 (7): 80-89
  60. [60] Sannigrahi M，Thandeeswaran R. Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm [J/OL].Journal of Engineering，2025，2025（1）：5430763.https://doi.org/10.1155/je/5430763.
  61. [61] Li J W，Pan Z S，Jiang K L. A Three-Dimensional Convolutional Neural Network for Dark Web Traffic Classification Based on Multi-channel Image Deep Learning [J/OL].Computers，2025，14（8）：295.https://doi.org/10.3390/computers14080295.
  62. Zhang Fan, Liu Siyuan Network traffic classification method based on global adaptive stride fully convolutional neural network [J]. Journal of Guilin Aerospace Industry Institute, 2024, 29 (5): 747-754
  63. Qin Kuangyu, Tang Haiyang, Xie Xiaoyang Research on Network Traffic Classification Method Based on Improved EfficientNetV2 [J]. Popular Science and Technology, 2023, 25 (12): 1-5
  64. Li Daoquan, Zhu Shengkai, Zhai Yuyang, etc Semi supervised network traffic classification based on feature selection and improvement using Tri training [J]. Computer Engineering and Applications, 2024, 60 (23): 275-285
  65. Hu Caifu, Wei Bo, Ren Ruibin Network traffic classification based on incremental learning from the perspective of spatial optimization [J/OL]. Computer Engineering, 2025:1-12 https://doi.org/10.19678/j.issn.1000-3428.0252067.
  66. Dai Qianyi, Zhang Bin, Guo Song, etc A blockchain network layer anomaly traffic detection method based on multi classifier integration [J]. Journal of Communications, 2023, 44 (3): 66-80

About the authors

Jiang Yifei (1998-), female, Han ethnicity, Beijing native, assistant researcher, master's student, research direction: network traffic classification.