计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 250200021-8.doi: 10.11896/jsjkx.250200021
林宏刚, 李彧涵
LIN Honggang, LI Yuhan
摘要： 随着网络流量分析技术的发展,对高质量流量生成的需求不断提升。然而现有流量生成方法主要关注包级特征,忽略了时序特性,不能满足要求。为提高生成流量的质量,提出一种改进的TimeGAN流量生成方法,采用GRU提取包级与时序特征,并结合多头局部-全局注意力机制提升特征融合能力,实现流量特征的均衡建模。同时,设计周期判别-动态解码策略,以生成动态长度的流量序列并保留周期性。从可用性与相似性两方面评估生成流量数据,结果表明,该方法在各项指标上均优于现有方法,能有效提升生成流量质量,更好地模拟真实的网络流量。
中图分类号:
| [1]ADELEKE O A,BASTIN N,GURKAN D.Network trafficgeneration:A survey and methodology[J].ACM Computing Surveys(CSUR),2022,55(2):1-23. [2]LU X L,LI Z L.IoT Device Recognition Method Combining Multimodal IoT Device Fingerprint and Ensemble Learning[J].Computer Science,2024,51(9):371-382. [3]SIVAROOPAN N,BANDARA D,MADARASINGHA C,et al.Netdiffus:Network traffic generation by diffusion models through time-series imaging[J].Computer Networks,2024,251:110616. [4]ANANDE T J,AL-SAADI S,LEESON M S.Generative adver-sarial networks for network traffic feature generation[J].International Journal of Computers and Applications,2023,45(4):297-305. [5]BENADDI H,JOUHARI M,IBRAHIMI K,et al.Adversarialattacks against iot networks using conditional gan based lear-ning[C]//GLOBECOM 2022－2022 IEEE Global Communications Conference.IEEE,2022:2788-2793. [6]GE Z,WU H,CHENG G,et al.NFlowGAN:High-Utility Privacy-Preserving Network Flow Synthesis Based on GAN[C]//ICC 2023－IEEE International Conference on Communications.IEEE,2023:4057-4062. [7]HUI S D,WANG H D,WANG Z H,et al.Knowledge Enhanced GAN for IoT Traffic Genera-tion[C]//Proceedings of the ACM Web Conference 2022(WWW ’22).Association for Computing Machinery,New York,NY,USA,2022:3336-3346. [8]ZHANG Y W,ZHANG Y C,WU Y,et al.Research on Improvement of Generation Adversarial Networks for Network Traffic Datasets Augmentation[J].Computer Engineering and Applications,2024,60(18):275-284. [9]KHOLGH D K,KOSTAKOS P.PAC-GPT:A novel approach to generating synthetic network traffic with GPT-3[J].IEEE Access,2023,11:114936-114951. [10]BANO S,CASSARÁ P,VALERIO L.Variational Autoencoders for Noise Resistant Traffic Generation in B5G Net-works[C]//2024 IEEE International Mediterranean Conference on Communications and Networking(MeditCom).IEEE,2024:13-18. [11]LI W,ZHANG C.A hidden markov model for condition monitoring of time series data in complex network systems[J].IEEE Transactions on Reliability,2023,72(4):1478-1492. [12]MESLET-MILLET F,MOUYSSET S,CHAPUT E.NeCST-Gen:An approach for realistic network traffic generation using deep learning[C]//GLOBECOM 2022－2022 IEEE Global Communications Conference.IEEE,2022:3108-3113. [13]LI J,ZHOU L,LI H,et al.Dynamic traffic feature camou-flaging via generative adversarial networks[C]//2019 IEEE Conference on Communications and Network Security(CNS).IEEE,2019:268-276. [14]SHAHID M R,BLANC G,JMILA H,et al.Gen-erative Deep Learning for Internet of Things Network Traffic Generation[C]//2020 IEEE 25th Pacific Rim International Symposium on Dependable Computing(PRDC),Perth,WA,Australia,2020:70-79. [15]YOON J,JARRETT D,SCHAAR M V D.Time-series Generative Adversarial Networks[C]//Neural Information Processing Systems(NeurIPS).2019. [16]MIETTINEN M,MARCHAL S,HAFEEZ I,et al.Iot sentinel:Au-tomated device-type identification for security enforcement in IoT[C]//2017 IEEE 37th International Conference on Distributed Computing Systems(ICDCS).IEEE,2017:2177-2184. [17]QU J,MA X,LI J.Trafficgpt:Breaking the token barrier for efficient long traffic analysis and generation[J].arXiv:2403.05822,2024. [18]ZHAO F,ZHANG M,ZHOU S,et al.Detection of network security traffic anomalies based on machine learning KNN method[J].Journal of Artificial Intelligence General Science(JAIGS).2024,1(1):209-218. [19]DONG S.Multi class SVM algorithm with active learning fornetwork traffic classification[J].Expert Systems with Applications,2021,176:114885. [20]LABAYEN V,MAGAÑA E,MORATÓ D,et al.Online classification of user activities using machine learning on network traffic[J].Computer Networks,2020,181:107557. [21]SONG Z,ZHAO Z,ZHANG F,et al.I ∧{2}$ RNN:An In-cremental and Interpretable Recurrent Neural Network for Encrypted Traffic Classification[J].IEEE Transactions on Dependable and Secure Computing(Early Access). [22]WANG Y,WANG F,TIAN Q,et al.Dynamic Bandwidth allo-cation algorithm based on traffic classification with the aid of LSTM and GRU for industrial passive optical networks[C]//2023 21st International Conference on Optical Communications and Networks(ICOCN).IEEE,2023:1-3. [23]KURITA T.Principal Component Analysis(PCA)[M]//Com-puter vision:a reference guide.Cham:Springer International Publishing,2021:1013-1016. |
|
||
首页