Encrypted Traffic Pre-Trained Model with Long-Range Dependency and Local Dynamic Perception

ZHANG Lei; LIU Xiao; ZHANG Longgang; HE Qing

doi:10.12263/DZXB.20260269

您当前的位置：

首页 >

文章列表页 >

Encrypted Traffic Pre-Trained Model with Long-Range Dependency and Local Dynamic Perception

PAPERS | 更新时间：2026-07-30

- Encrypted Traffic Pre-Trained Model with Long-Range Dependency and Local Dynamic Perception
- ACTA ELECTRONICA SINICA Vol. 54, Issue 4, Pages: 1835-1856(2026)
- 作者机构：
  
  1.重庆大学微电子与通信工程学院，重庆 400044
  2.重庆市生物感知与多模态智能信息处理重点实验室，重庆 400044
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(92570110;62271090);Chongqing Natural Science Fund(CSTB2024NSCQ-JQX0038)
- DOI：10.12263/DZXB.20260269
  CLC： TP393;
- Received：02 March 2026，
  
  Accepted：14 April 2026，
  
  Online First：25 May 2026，
  
  Published：25 April 2026
- 稿件说明：
移动端阅览
张磊, 刘晓, 张龙港, 等. 基于长程依赖与局部动态感知的加密流量预训练模型构建[J]. 电子学报, 2026, 54(04): 1835-1856.

ZHANG Lei, LIU Xiao, ZHANG Longgang, et al. Encrypted Traffic Pre-Trained Model with Long-Range Dependency and Local Dynamic Perception[J]. Acta Electronica Sinica, 2026, 54(04): 1835-1856.
张磊, 刘晓, 张龙港, 等. 基于长程依赖与局部动态感知的加密流量预训练模型构建[J]. 电子学报, 2026, 54(04): 1835-1856. DOI：10.12263/DZXB.20260269

ZHANG Lei, LIU Xiao, ZHANG Longgang, et al. Encrypted Traffic Pre-Trained Model with Long-Range Dependency and Local Dynamic Perception[J]. Acta Electronica Sinica, 2026, 54(04): 1835-1856. DOI：10.12263/DZXB.20260269

摘要

网络流量表征与分类在网络管理和安全中发挥重要作用。由于仅依赖局部卷积运算，传统的卷积神经网络（Convolutional Neural Network，CNN）已不足以应对当前网络流量的复杂性和变化性。基于Transformer架构的方法在流量序列处理中取得了一定效果，但其自注意力机制带来的平方级计算复杂度导致了较高的资源消耗，且在处理长序列时效率较低，同时该架构未优先考虑时间依赖关系，导致局部序列一致性容易丢失。近期引入的状态空间模型（State-Space Models，SSM）Mamba实现了随序列长度线性扩展的计算效率，在局部动态感知和长序列处理方面具有优势，但由于其将历史信息压缩至固定维度的隐藏状态中，限制了对长距离依赖和全局流量特征的获取能力。针对上述问题，本文提出一种基于长程依赖与局部动态感知的加密网络流量预训练模型（Encrypted Traffic pre-trained model with Long-range Dependency and dynamic Perception，ET-LDP）。该模型摒弃了传统的架构拼接，选择依据网络流量包含流级别全局统计模式与字节级别局部语义的多粒度特性，从流量特征的角度将多种类型的模块进行集成，构建了跨机架构协同结构。ET-LDP在Mamba层内部引入混合专家（Mixture of Experts，MoE）机制，通过共享参数与私有门控相结合的路由策略，模型将不同语义的token动态分配给特定专家处理，在保持较低计算开销的同时提高了模型容量与局部特征的感知能力。在提取全局长程依赖方面，模型设计了混合注意力模块，首先通过代理注意力（Agent Attention）利用代理token聚合局部信息并减少冗余计算，然后结合softmax自注意力完成细粒度的上下文关联提取。为解决Mamba模块与注意力模块在信息流向与特征空间上的差异，本文进一步设计了跨架构桥接组件，通过信息交互机制实现了两类异构特征的结构性对齐与相互补充。这种灵活的架构允许针对特定资源和目标进行配置，从而兼顾各自的优势。考虑到网络流量和网络任务的多样性，ET-LDP结合自监督机制，从大规模无标签流量数据中预训练通用表征。在虚拟专用网络（Virtual Private Network，VPN）、洋葱路由器（The onion router，Tor）、恶意软件及跨平台应用等7个公开网络流量数据集的评估表明，本文提出的ET-LDP模型在分类性能上均优于目前的最优（State Of The Art，SOTA）方法。在采用新加密协议的中国科技网TLS 1.3流量（China Science and Technology NETwork-TLS 1.3，CSTNET-TLS 1.3）数据集上，相较于同类最优的模型准确率提升了0.013 2。在效率测试中，当批大小为64时，该模型的推理显存占用为同等规模Transformer模型的0.6倍，在吞吐量与计算延迟上表现出较好的平衡。

Abstract

Network traffic representation and classification plays an important role in network security and management. Due to local convolution operations

traditional convolutional neural networks (CNN) are insufficient to handle the complexity and variability of modern network traffic. Although Transformer-based methods have achieved certain results in traffic sequence processing

the quadratic computational complexity of their self-attention mechanisms leads to high resource consumption and low efficiency when processing long sequences. Meanwhile

this architecture does not prioritize time dependencies

leading to a loss of local sequence consistency. The recently introduced state-space model (SSM) Mamba achieves computational efficiency that scales linearly with sequence length

showing advantages in local dynamic perception and long-sequence processing. However

because it compresses historical information into a fixed-dimensional hidden state

its ability to capture long-range dependencies and global traffic features is limited. To address these issues

this paper proposes encrypted traffic pre-trained model with long-range dependency and dynamic perception (ET-LDP)

an encrypted network traffic pre-trained model based on long-range dependency and local dynamic perception. Instead of traditional architecture concatenation

the model integrates multiple types of modules from the perspective of traffic characteristics. Based on the multi-granularity nature of network traffic

which includes flow-level global statistical patterns and byte-level local semantics

a cross-architecture collaborative structure is constructed. ET-LDP introduces the mixture-of-experts (MoE) mechanism inside the Mamba layer. Through a routing strategy combining shared parameters and private gating

the model dynamically allocates tokens with different semantics to specific experts

which improves model capacity and local feature perception capabilities while maintaining a low computational overhead. For extracting global long-range dependencies

the model designs a mixed attention module. It first utilizes Agent Attention to aggregate local information and reduce redundant computation via agent tokens

and then combines softmax self-attention to complete fine-grained context association extraction. To solve the differences in information flow and feature space between the Mamba module and the attention module

this paper further designs cross-architecture bridging components

realizing structural alignment and mutual complementation of the two heterogeneous features through an information interaction mechanism. This flexible architecture allows configuration for specific resources and targets. Considering the diversity of network traffic and tasks

ET-LDP adopts a self-supervised learning mechanism to pre-train generalized representations from large-scale unlabeled traffic data. Evaluations on 7 public network traffic datasets

covering virtual private network (VPN)

the onion router (Tor)

malware

and cross-platform applications

indicate that the proposed ET-LDP model outperforms state of the art (SOTA) methods in classification performance. On the China science and technology network-TLS 1.3 (CSTNET-TLS 1.3) dataset using new encryption protocols

the accuracy is improved by 0.013 2 compared to the best-performing counterpart. In efficiency tests

at a batch size of 64

the inference memory consumption of the model is 0.6 times that of similar Transformer models

showing a good balance in throughput and computational latency.

关键词

Keywords

references

Bujlow T , Carela-Español V , Barlet-Ros P . Independent comparison of popular DPI tools for traffic classification [J ] . Computer Networks , 2015 , 76 : 75 - 89 . DOI: 10.1016/j.comnet.2014.11.001 http://dx.doi.org/10.1016/j.comnet.2014.11.001

任杰 , 王洪超 , 王钦定 , 等 . 服务感知网络 [J ] . 电子学报 , 2025 , 53 ( 2 ): 371 - 384 .

Ren Jie , Wang Hongchao , Wang Qinding , et al . Service aware network [J ] . Acta Electronica Sinica , 2025 , 53 ( 2 ): 371 - 384 . (in Chinese)

徐鹏 , 林森 . 基于C4.5决策树的流量分类方法 [J ] . 软件学报 , 2009 , 20 ( 10 ): 2692 - 2704 . DOI: 10.3724/SP.J.1001.2009.03444 http://dx.doi.org/10.3724/SP.J.1001.2009.03444

Xu Pen , Lin Sen . Internet traffic classification using C4.5 decision tree [J ] . Journal of Software , 2009 , 20 ( 10 ): 2692 - 2704 . (in Chinese) . DOI: 10.3724/SP.J.1001.2009.03444 http://dx.doi.org/10.3724/SP.J.1001.2009.03444

Taylor V F , Spolaor R , Conti M , et al . Robust smartphone app identification via encrypted network traffic analysis [J ] . IEEE Transactions on Information Forensics and Security , 2018 , 13 ( 1 ): 63 - 78 . DOI: 10.1109/TIFS.2017.2737970 http://dx.doi.org/10.1109/TIFS.2017.2737970

Van Ede T , Bortolameotti R , Continella A , et al . FlowPrint: Semi-supervised mobile-app fingerprinting on encrypted network traffic [C/OL ] // Proceedings of the 27th Annual Network and Distributed System Security Symposium , 2020 . https://dblp.org/db/conf/ndss/ndss2020.html#conf/ndss/EdeBCRDLCSP20 https://dblp.org/db/conf/ndss/ndss2020.html#conf/ndss/EdeBCRDLCSP20 . DOI: 10.14722/ndss.2020.24412 http://dx.doi.org/10.14722/ndss.2020.24412

Liu Chang , He Longtao , Xiong Gang , et al . FS-Net: A flow sequence network for encrypted traffic classification [C ] // Proceedings of the IEEE Conference on Computer Communications . Piscataway : IEEE , 2019 : 1171 - 1179 . DOI: 10.1109/INFOCOM.2019.8737507 http://dx.doi.org/10.1109/INFOCOM.2019.8737507

张小莉 , 程光 , 张慰慈 . 基于改进深度卷积神经网络的网络流量分类方法 [J ] . 中国科学: 信息科学 , 2021 , 51 ( 1 ): 56 - 74 . DOI: 10.1360/ssi-2019-0213 http://dx.doi.org/10.1360/ssi-2019-0213

Zhang Xiaoli , Cheng Guang , Zhang Weici . Network traffic classification method based on improved deep convolutional neural network [J ] . Scientia Sinica Informationis , 2021 , 51 ( 1 ): 56 - 74 . (in Chinese) . DOI: 10.1360/ssi-2019-0213 http://dx.doi.org/10.1360/ssi-2019-0213

Zhou Guangmeng , Guo Xiongwen , Liu Zhuotao , et al . TrafficFormer: An efficient pre-trained model for traffic data [C ] // 2025 IEEE Symposium on Security and Privacy (SP) . Piscataway : IEEE , 2025 : 1844 - 1860 . DOI: 10.1109/sp61157.2025.00102 http://dx.doi.org/10.1109/sp61157.2025.00102

Cui Tianyu , Lin Xinjie , Li Sijia , et al . TrafficLLM: Enhancing large language models for network traffic analysis with generic traffic representation [PP/OL ] . V2. arXiv ( 2025-04-15 ) [ 2026-02-25 ] . https://arxiv.org/abs/2504.04222v2 https://arxiv.org/abs/2504.04222v2 .

Lin Xinjie , Xiong Gang , Gou Gaopeng , 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 : ACM , 2022 : 633 - 642 . DOI: 10.48550/arXiv.2202.06335 http://dx.doi.org/10.48550/arXiv.2202.06335

Gu A , Dao T . Mamba: Linear-time sequence modeling with selective state spaces [PP/OL ] . V2.arXiv ( 2024-05-31 ) [ 2025-11-13 ] . https://arxiv.org/abs/2312.00752v2 https://arxiv.org/abs/2312.00752v2 .

Zhao Ruijie , Zhan Mingwei , Deng Xianwen , et al . A novel self-supervised framework based on masked autoencoder for traffic classification [J ] . IEEE/ACM Transactions on Networking , 2024 , 32 ( 3 ): 2012 - 2025 . DOI: 10.1109/tnet.2023.3335253 http://dx.doi.org/10.1109/tnet.2023.3335253

Wang Qineng , Qian Chen , Li Xiaochang , et al . Lens: A foundation model for network traffic in cybersecurity [PP/OL ] . V3. arXiv ( 2024-03-29 ) [ 2025-11-13 ] . https://arxiv.org/abs/2402.03646v3 https://arxiv.org/abs/2402.03646v3 .

何帅 , 张京超 , 徐笛 , 等 . 基于对比学习和预训练Transformer的流量隐匿数据检测方法 [J ] . 通信学报 , 2025 , 46 ( 3 ): 221 - 233 .

He Shuai , Zhang Jingchao , Xu Di , et al . Traffic concealed data detection method based on contrastive learning and pre-trained Transformer [J ] . Journal on Communications , 2025 , 46 ( 3 ): 221 - 233 . (in Chinese)

Park J , Park J , Xiong Zheyang , et al . Can mamba learn how to learn: A comparative study on in-context learning tasks [C/OL ] // Proceedings of the 41st International Conference on Machine Learning , 2024 : 39793 - 39812 . https://dblp.uni-trier.de/db/conf/icml/icml2024.html#conf/icml/ParkPXLCO0P24 https://dblp.uni-trier.de/db/conf/icml/icml2024.html#conf/icml/ParkPXLCO0P24 .

Lieber O , Lenz B , Bata H , et al . Jamba: A hybrid transformer-mamba language model [PP/OL ] . V2. arXiv ( 2024-07-03 ) [ 2025-11-13 ] . https://arxiv.org/abs/2403.19887v2 https://arxiv.org/abs/2403.19887v2 .

Hatamizadeh A , Kautz J . MambaVision: A hybrid mamba-transformer vision backbone [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2025 : 25261 - 25270 . DOI: 10.1109/cvpr52734.2025.02352 http://dx.doi.org/10.1109/cvpr52734.2025.02352

Shi Jingze , Xie Ting , Wu Bingheng , et al . OTCE: Hybrid SSM and attention with cross domain mixture of experts to construct observer-thinker-conceiver-expresser [PP/OL ] . V3. arXiv ( 2024-07-20 ) [ 2025-11-13 ] . https://arxiv.org/abs/2406.16495v3 https://arxiv.org/abs/2406.16495v3 .

Su Jinzhao , Huang Zhenhua , Wang Changdong , et al . MLSA4Rec: Mamba combined with low-rank decomposed self-attention for sequential recommendation [J ] . IEEE Transactions on Computational Social Systems , 2026 , 13 ( 2 ): 1819 - 1834 . DOI: 10.1109/tcss.2025.3623273 http://dx.doi.org/10.1109/tcss.2025.3623273

Han Dongchen , Ye Tianzhu , Han Yizeng , et al . Agent attention: On the integration of softmax and linear attention [C ] // Proceedings of the 18th European Conference on Computer Vision . Heidelberg : Springer , 2025 : 124 - 140 . DOI: 10.1007/978-3-031-72973-7_8 http://dx.doi.org/10.1007/978-3-031-72973-7_8

He Hongye , Yang Zhiguo , Chen Xiangning . PERT: Payload encoding representation from transformer for encrypted traffic classification [C ] // Proceedings of the 2020 ITU Kaleidoscope: Industry-Driven Digital Transformation (ITU K) . Piscataway : IEEE , 2020 : 9303204 . DOI: 10.23919/ituk50268.2020.9303204 http://dx.doi.org/10.23919/ituk50268.2020.9303204

Meng Xuying , Lin Chungang , Wang Yequan , et al . NetGPT: Generative pretrained transformer for network traffic [PP/OL ] . V3.arXiv ( 2025-08-28 ) [ 2025-11-13 ] . https://arxiv.org/abs/2304.09513v3 https://arxiv.org/abs/2304.09513v3 . DOI: 10.1109/isaeece66033.2025.11159936 http://dx.doi.org/10.1109/isaeece66033.2025.11159936

Zhao Ruijie , Zhan Mingwei , Deng Xianwen , et al . Yet another traffic classifier: A masked autoencoder based traffic transformer with multi-level flow representation [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 4 ): 5420 - 5427 . DOI: 10.1609/aaai.v37i4.25674 http://dx.doi.org/10.1609/aaai.v37i4.25674

Liu Xiao , Zhang Chenxu , Huang Fuxiang , et al . Vision mamba: A comprehensive survey and taxonomy [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2026 , 37 ( 2 ): 505 - 525 . DOI: 10.1109/tnnls.2025.3610435 http://dx.doi.org/10.1109/tnnls.2025.3610435

Waleffe R , Byeon W , Riach D , et al . An empirical study of mamba-based language models [PP/OL ] . V1. arXiv ( 2024-06-12 ) [ 2025-11-13 ] . https://arxiv.org/abs/2406.07887v1 https://arxiv.org/abs/2406.07887v1 .

Wang T , Xie X , Wang W , et al . Netmamba: Efficient network traffic classification via pre-training unidirectional mamba [C ] // 2024 IEEE 32nd International Conference on Network Protocols . Piscataway : IEEE , 2024 : 10858569 . DOI: 10.1109/ICNP61940.2024.10858569 http://dx.doi.org/10.1109/ICNP61940.2024.10858569

Katharopoulos A , Vyas A , Pappas N , et al . Transformers are RNNs: Fast autoregressive transformers with linear attention [C/OL ] // Proceedings of the 37th International Conference on Machine Learning , 2020 : 5156 - 5165 . https://dblp.org/db/conf/icml/icml2020.html#conf/icml/KatharopoulosV020 https://dblp.org/db/conf/icml/icml2020.html#conf/icml/KatharopoulosV020 . DOI: 10.48550/arXiv.2006.16236 http://dx.doi.org/10.48550/arXiv.2006.16236

Qin Zhen , Sun Weixuan , Deng Hui , et al . cosFormer: Rethinking Softmax in attention [C/OL ] // Proceedings of the 10th International Conference on Learning Representations , 2022 : 8304 - 8318 . https://dblp.org/db/conf/iclr/iclr2022.html#conf/iclr/QinSDLWLYKZ22 https://dblp.org/db/conf/iclr/iclr2022.html#conf/iclr/QinSDLWLYKZ22 . DOI: 10.48550/arXiv.2202.08791 http://dx.doi.org/10.48550/arXiv.2202.08791

Choromanski K M , Likhosherstov V , Dohan D , et al . Rethinking attention with performers [C/OL ] // Proceedings of the 9th International Conference on Learning Representations , 2021 : 1060 - 1097 . https://dblp.org/db/conf/iclr/iclr2021.html#conf/iclr/ChoromanskiLDSG21 https://dblp.org/db/conf/iclr/iclr2021.html#conf/iclr/ChoromanskiLDSG21 .

Shen Zhuoran , Zhang Mingyuan , Zhao Haiyu , et al . Efficient attention: Attention with linear complexities [C ] // Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2021 : 3530 - 3538 . DOI: 10.1109/wacv48630.2021.00357 http://dx.doi.org/10.1109/wacv48630.2021.00357

Xiong Yunyang , Zeng Zhanpeng , Chakraborty R , et al . Nyströmformer: A nyström-based algorithm for approximating self-attention [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 16 ): 14138 - 14148 . DOI: 10.1609/aaai.v35i16.17664 http://dx.doi.org/10.1609/aaai.v35i16.17664

Lu Jiachen , Yao Jinghan , Zhang Junge , et al . SOFT: Softmax-free transformer with linear complexity [C ] // Proceedings of the 35th International Conference on Neural Information Processing Systems . New York : ACM , 2021 : 1629 . DOI: 10.48550/arXiv.2110.11945 http://dx.doi.org/10.48550/arXiv.2110.11945

Han Dongchen , Pan Xuran , Han Yizeng , et al . FLatten transformer: Vision transformer using focused linear attention [C ] // Proceedings of the IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2023 : 5938 - 5948 . DOI: 10.1109/iccv51070.2023.00548 http://dx.doi.org/10.1109/iccv51070.2023.00548

Jacobs R A , Jordan M I , Nowlan S J , et al . Adaptive mixtures of local experts [J ] . Neural Computation , 1991 , 3 ( 1 ): 79 - 87 . DOI: 10.1162/neco.1991.3.1.79 http://dx.doi.org/10.1162/neco.1991.3.1.79

Jordan M I , Jacobs R A . Hierarchical mixtures of experts and the EM algorithm [J ] . Neural Computation , 1994 , 6 ( 2 ): 181 - 214 . DOI: 10.1007/978-1-4471-2097-1_113 http://dx.doi.org/10.1007/978-1-4471-2097-1_113

Shazeer N , Mirhoseini A , Maziarz K , et al . Outrageously large neural networks: The sparsely-gated mixture-of-experts layer [C/OL ] // Proceedings of the 5th International Conference on Learning Representations , 2017 : 878 - 896 . https://dblp.uni-trier.de/db/conf/iclr/iclr2017.html#conf/iclr/ShazeerMMDLHD17 https://dblp.uni-trier.de/db/conf/iclr/iclr2017.html#conf/iclr/ShazeerMMDLHD17 . DOI: 10.48550/arXiv.1701.06538 http://dx.doi.org/10.48550/arXiv.1701.06538

Cai Weilin , Jiang Juyong , Wang Fan , et al . A survey on mixture of experts in large language models [J ] . IEEE Transactions on Knowledge and Data Engineering , 2025 , 37 ( 7 ): 3896 - 3915 . DOI: 10.1109/TKDE.2025.3554028 http://dx.doi.org/10.1109/TKDE.2025.3554028

Riquelme C , Puigcerver J , Mustafa B , et al . Scaling vision with sparse mixture of experts [C ] // Proceedings of the 35th International Conference on Neural Information Processing Systems . New York : ACM , 2021 : 657 . DOI: 10.48550/arXiv.2106.05974 http://dx.doi.org/10.48550/arXiv.2106.05974

Kudugunta S , Huang Yanping , Bapna A , et al . Beyond distillation: Task-level mixture-of-experts for efficient inference [C ] // Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2021 . Stroudsburg : ACL , 2021 : 3577 - 3599 . DOI: 10.18653/v1/2021.findings-emnlp.304 http://dx.doi.org/10.18653/v1/2021.findings-emnlp.304

Lin Junyang , Rui Men , Yang An , et al . M6: A Chinese multimodal pretrainer [PP/OL ] . V4.arXiv ( 2021-05-29 ) [ 2025-11-13 ] . https://arxiv.org/abs/2103.00823v4 https://arxiv.org/abs/2103.00823v4 . DOI: 10.48550/arXiv.2103.00823 http://dx.doi.org/10.48550/arXiv.2103.00823

Fedus W , Dean J , Zoph B . A review of sparse expert models in deep learning [PP/OL ] . V1.arXiv ( 2022-09-04 ) [ 2025-11-13 ] . https://arxiv.org/abs/2209.01667v1 https://arxiv.org/abs/2209.01667v1 .

Wang Wenhai , Xie Enze , Li Xiang , et al . Pyramid vision transformer: A versatile backbone for dense prediction without convolutions [C ] // Proceedings of the IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 548 - 558 . DOI: 10.48550/arXiv.2102.12122 http://dx.doi.org/10.48550/arXiv.2102.12122

Liu Ze , Lin Yutong , Cao Yue , et al . Swin transformer: Hierarchical vision transformer using shifted windows [C ] // Proceedings of the IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2021 : 9992 - 10002 . DOI: 10.48550/arXiv.2103.14030 http://dx.doi.org/10.48550/arXiv.2103.14030

Alwhbi I A , Zou C C , Alharbi R N . Encrypted network traffic analysis and classification utilizing machine learning [J ] . Sensors , 2024 , 24 ( 11 ): 3509 . DOI: 10.3390/s24113509 http://dx.doi.org/10.3390/s24113509

Devlin J , Chang Mingwei , Lee K , et al . BERT: Pre-training of deep bidirectional transformers for language understanding [C ] // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies . Stroudsburg : ACL , 2019 : 4171 - 4186 . DOI: 10.18653/v1/n19-1423 http://dx.doi.org/10.18653/v1/n19-1423

Ucar I , Morato D , Magaña E , et al . Duplicate detection methodology for IP network traffic analysis [C ] // Proceedings of the 2013 IEEE International Workshop on Measurements & Networking (M&N) . Piscataway : IEEE , 2013 : 161 - 166 . DOI: 10.1109/iwmn.2013.6663796 http://dx.doi.org/10.1109/iwmn.2013.6663796

Ali Ali A , Zimerman I , Wolf L . The hidden attention of mamba models [C ] // Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics . Stroudsburg : ACL , 2025 : 1516 - 1534 . DOI: 10.18653/v1/2025.acl-long.76 http://dx.doi.org/10.18653/v1/2025.acl-long.76

Draper-Gil G , Lashkari A H , Mamun M 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 : SciTePress , 2016 : 407 - 414 . DOI: 10.5220/0005740704070414 http://dx.doi.org/10.5220/0005740704070414

Habibi Lashkari A , Draper Gil G , Mamun M S I , et al . Characterization of tor traffic using time based features [C ] // International Conference on Information Systems Security and Privacy . Setúbal : SciTePress , 2017 , 2 : 253 - 262 . DOI: 10.5220/0006105602530262 http://dx.doi.org/10.5220/0006105602530262

Wang Wei , Zhu Ming , Zeng Xuewen , et al . Malware traffic classification using convolutional neural network for representation learning [C ] // 2017 International Conference on Information Networking (ICOIN) . Piscataway : IEEE , 2017 : 712 - 717 . DOI: 10.1109/ICOIN.2017.7899588 http://dx.doi.org/10.1109/ICOIN.2017.7899588

Dadkhah S , Mahdikhani H , Danso P K , et al . Towards the development of a realistic multidimensional IoT profiling dataset [C ] // Proceedings of the 2022 19th Annual International Conference on Privacy , Security & Trust (PST) . Piscataway : IEEE , 2022 : 9851966 . DOI: 10.1109/pst55820.2022.9851966 http://dx.doi.org/10.1109/pst55820.2022.9851966

Liu Liming , Li Ruoyu , Li Qing , et al . FlowletFormer: Network behavioral semantic aware pre-training model for traffic classification [PP/OL ] . V1. arXiv ( 2025-08-27 ) [ 2025-11-13 ] . https://arxiv.org/abs/2508.19924v1 https://arxiv.org/abs/2508.19924v1 . DOI: 10.1109/access.2025.3545117 http://dx.doi.org/10.1109/access.2025.3545117

Park J T , Choi Y S , Cho B S , et al . Multi-level pre-training for encrypted network traffic classification [J ] . IEEE Access , 2025 , 13 : 68643 - 68659 . DOI: 10.1109/access.2025.3559068 http://dx.doi.org/10.1109/access.2025.3559068

Fedus W , Zoph B , Shazeer N . Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity [J ] . The Journal of Machine Learning Research , 2022 , 23 ( 1 ): 120 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

RCS Reduction Method for Sparse Array Dual-Subarray Based on MAAM-LKN Model

Lightweight Intrusion Detection in the Edge Internet of Things with Dual-Teacher Distillation

Heterogeneous Graph-Based Identification of Critical Relays in Tor Networks

MSGPose: Monocular Single-Person 3D Human Pose Estimation Via Multi-Semantic Graph Convolution and Graph-Guided State Space Models

FF-STDP: A Forward-Forward STDP-Based Energy-Efficient SNN Accelerator with On-Chip Learning

Related Author

ZHANG Lei

LIU Xiao

ZHANG Longgang

HE Qing

JI Lixia

CHEN Yiqiao

REN Zhigang

ZENG Hao

Related Institution

Chongqing Key Laboratory of Bio-perception Multimodal Intelligent Information Processing

School of Electrical and Electronic Engineering, Chongqing University of Technology

Southwest Electronic Technology Institute

Xi’an University of Posts and Telecommunications

Hangzhou Dianzi University

⁰