参考文献:
[1]Google.Google透明度报告[EB/OL].2022[2022-03-06].https://transparencyreport.google.com/https/overview.
[2]陈良臣, 高曙, 刘宝旭, 等. 网络加密流量识别研究进展及发展趋势[J].信息网络安全,2019(3):7.
[3]Anderson B, McGrew D. Identifying encrypted malware traffic with contextual flow data[C]//Proceedingsofthe2016ACMworkshoponartificialintelligenceandsecurity.2016:35-46.
[4]De Haan P, Jayaraman D, Levine S.Causal confusion in imitation learning[J].Advances inNeuralInformation Processing Systems,2019,32.
[5]Dainotti A, Pescape A, Claffy K C. Issues and future directions in traffic classification[J/OL].IEEENetwork,2012, 26(1):35-40.DOI: 10.1109/MNET.2012.6135854.
[6]ConstantinouF,MavrommatisP.Identifyingknownandunknownpeer-to-peertraffic[C/OL]//FifthIEEEInternationalSymposiumonNetworkComputingandApplications(NCA’06).2006:93-102.DOI: 10.1109/NCA.2006.34.
[7]ThayC,VisoottivisethV,MongkolluksameeS.P2ptrafficclassificationforresidentialnetwork[C/OL]//2015 International Computer Science and Engineering Conference (ICSEC).2015:1-6.DOI: 10.1109/ICSEC.2015.7401433.
[8]HafeezS.Deeppacketinspection[J].EetimesCom,2016(11):585-589.
[9]HaffnerP.Acas:Automatedconstructionofapplicationsignatures[C]//SIGCOMM’05Work-shops,Augst.2005.
[10]Wright C, Monrose F, Masson G M. Hmm profiles for network traffic classification[C]//AcmWorkshoponVisualization&DataMiningforComputerSecurity.2004:9.
[11]WrightCV,MonroseF,MassonGM.Oninferringapplicationprotocolbehaviorsinencryptednetworktraffic[J].JournalofMachineLearningResearch,2006,6(4):2745-2769.
[12]Alshammari R, Zincir-Heywood A N. Machine learning based encrypted traffic classification:Identifying ssh and skype[C/OL]//2009 IEEE Symposium on Computational Intelligence forSecurityand DefenseApplications.2009:1-8.DOI:10.1109/CISDA.2009.5356534.
[13]Alshammari R, Nur Zincir-Heywood A. A flow based approach for ssh traffic detection[C/OL]//2007 IEEE International Conference on Systems, Man and Cybernetics. 2007: 296-301. DOI:10.1109/ICSMC.2007.4414006.
[14]Dusi M, Este A, Gringoli F, et al. Using gmm and svm-based techniques for the classification ofssh-encrypted traffic[C/OL]//2009 IEEE International Conference on Communications. 2009:1-6.DOI: 10.1109/ICC.2009.5199557.
[15]Sun G L, Xue Y, Dong Y, et al. An novel hybrid method for effectively classifying encryptedtraffic[C/OL]//2010 IEEE Global Telecommunications Conference GLOBECOM 2010. 2010:1-5.DOI: 10.1109/GLOCOM.2010.5683649.
[16]Gu R, Wang H, Ji Y. Early traffic identification using bayesian networks[C/OL]//2010 2nd IEEEInternationalConference on Network Infrastructure and Digital Content. 2010: 564-568. DOI:10.1109/ICNIDC.2010.5657833.
[17]TabatabaeiTS,KarrayF,KamelM. Earlyinternettrafficrecognitionbasedonmachinelearningmethods[C/OL]//2012 25th IEEE Canadian Conference on Electrical and Computer Engineer-ing(CCECE).2012:1-5.DOI: 10.1109/CCECE.2012.6335034.
[18]HuijunC,HongS,HongZ.Earlyrecognitionofinternetserviceflow[C/OL]//201322ndWire-less and Optical Communication Conference. 2013: 464-468. DOI: 10.1109/WOCC.2013.6676412.
[19]Draper-GilG,LashkariAH,MamunMSI,etal.Characterizationofencryptedandvpntrafficusingtime-related features[C]//ICISSP.2016.
[20]Yamansavascilar B, Guvensan M A, Yavuz A G, et al.Application identification via net-work traffic classification[C/OL]//2017 International Conference on Computing, NetworkingandCommunications (ICNC).2017:843-848.DOI: 10.1109/ICCNC.2017.7876241.
[21]Lashkari A H, Draper-Gil G, Mamun M S I, et al.Characterization of tor traffic using timebasedfeatures[C]//ICISSP.2017.
[22]Shahbar K, Zincir-Heywood A N.How far can we push flow analysis to identify encryptedanonymity network traffic?[C/OL]//NOMS 2018 - 2018 IEEE/IFIP Network Operations andManagementSymposium.2018:1-6.DOI: 10.1109/NOMS.2018.8406156.
[23]ShahbarK,Zincir-HeywoodAN.Packetmomentumforidentificationofanonymitynetworks[C/OL]//Journal of Cyber Security and Mobility: volume 6. 2017: 27-56. DOI: https://doi.org/10.13052/jcsm2245-1439.612.
[24]Wang Z. The applications of deep learning on traffic identification[C]//Black Hat USA 2015.2015.
[25]LotfollahiM,SiavoshaniMJ,ZadeRSH,etal.Deeppacket:Anovelapproachforencryptedtrafficclassificationusingdeeplearning[J].Soft Computing,2020,24(3):1999-2012.
[26]Wang W, Zhu M, Wang J, et al. End-to-end encrypted traffic classification with one-dimensionalconvolution neural networks[C]//2017 IEEE International Conference on Intelligence and Se-curity Informatics(ISI).IEEE, 2017:43-48.
[27]Wang W, Zhu M, Zeng X, et al. Malware traffic classification using convolutional neural net-workforrepresentationlearning[C]//2017InternationalConferenceonInformationNetworking(ICOIN).IEEE, 2017:712-717.
[28]Lim H K, Kim J B, Heo J S, et al. Packet-based network traffic classification using deep learning[C/OL]//2019InternationalConferenceonArtificialIntelligenceinInformationandCommuni-cation(ICAIIC).2019:046-051.DOI: 10.1109/ICAIIC.2019.8669045.
[29]He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings oftheIEEE conferenceon computer vision and pattern recognition.2016:770-778.
[30]Rezaei S, Liu X.How to achieve high classification accuracy with just a few labels: A semi-supervisedapproachusing sampledpackets[J].ArXiv,2019, abs/1812.09761.
[31]ZhangJ,LiF,YeF,etal.Autonomousunknown-applicationfilteringandlabelingfordl-basedtraffic classifier update[C/OL]//IEEE INFOCOM 2020 - IEEE Conference on Computer Com-munications.2020:397-405.DOI: 10.1109/INFOCOM41043.2020.9155292.
[32]薛文龙, 于炯, 郭志琦, 等. 基于特征融合卷积神经网络的端到端加密流量分类[J].计算机工程与应用, 2021, 57(18):8.
[33]Lopez-Martin M, Carro B, Sanchez-Esguevillas A, et al.Network traffic classifier with con-volutional and recurrent neural networks for internet of things[J/OL].IEEE Access, 2017, 5:18042-18050.DOI: 10.1109/ACCESS.2017.2747560.
[34]Liu C, He L, Xiong G, et al. Fs-net: A flow sequence network for encrypted traffic classifica-tion[C/OL]//IEEE INFOCOM 2019 - IEEE Conference on Computer Communications. 2019:1171-1179.DOI: 10.1109/INFOCOM.2019.8737507.
[35]Wang X, Chen S, Su J.App-net: A hybrid neural network for encrypted mobile traffic clas-sification[C/OL]//IEEE INFOCOM 2020 - IEEE Conference on Computer CommunicationsWorkshops (INFOCOM WKSHPS). 2020: 424-429. DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162891.
[36]Wang M, Zheng K, Luo D, et al. An encrypted traffic classification framework based on con-volutionalneuralnetworksandstackedautoencoders[C/OL]//2020IEEE6thInternationalCon-ference on Computer and Communications (ICCC). 2020: 634-641. DOI: 10.1109/ICCC51575.2020.9344978.
[37]Goodfellow I, Pouget-Abadie J, Mirza M, et al.Generative adversarial nets[J].Advances inneuralinformation processing systems, 2014, 27.
[38]WangP,LiS,YeF,etal.Packetcgan:Exploratorystudyofclassimbalanceforencryptedtrafficclassification using cgan[C/OL]//ICC 2020 - 2020 IEEE International Conference on Commu-nications(ICC).2020:1-7.DOI: 10.1109/ICC40277.2020.9148946.
[39]MirzaM,OsinderoS.Conditionalgenerativeadversarialnets[J].arXivpreprintarXiv:1411.1784,2014.
[40]JapkowiczN,etal.Learningfromimbalanceddatasets:acomparisonofvariousstrategies[C]//AAAI workshop on learning from imbalanced data sets: volume 68. AAAI Press Menlo Park,CA,2000:10-15.
[41]ChawlaNV,BowyerKW,HallLO,etal.Smote:syntheticminorityover-samplingtechnique[J].Journal of artificial intelligenceresearch,2002, 16:321-357.
[42]Guo Y, Xiong G, Li Z, et al. Combating imbalance in network traffic classification using ganbased oversampling[C/OL]//2021 IFIP Networking Conference (IFIP Networking). 2021: 1-9.DOI:10.23919/IFIPNetworking52078.2021.9472777.
[43]Li C, Xu T, Zhu J, et al. Triple generative adversarial nets[J]. Advances in neural informationprocessingsystems,2017, 30.
[44]Aouedi O, Piamrat K, Bagadthey D. A semi-supervised stacked autoencoder approach for net-worktrafficclassification[C/OL]//2020IEEE28thInternationalConferenceonNetworkProto-cols(ICNP).2020:1-6.DOI: 10.1109/ICNP49622.2020.9259390.
[45]Xing J, Wu C.Detecting anomalies in encrypted traffic via deep dictionary learning[C/OL]//IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFO-COMWKSHPS).2020:734-739.DOI:10.1109/INFOCOMWKSHPS50562.2020.9162940.
[46]Van den Oord A, Li Y, Vinyals O. Representation learning with contrastive predictive coding[J].arXiv e-prints, 2018:arXiv-1807.
[47]He K, Fan H, Wu Y, et al.Momentum contrast for unsupervised visual representation learn-ing[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.2020:9729-9738.
[48]Chen T, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visualrepresentations[C]//Internationalconferenceon machinelearning.PMLR, 2020:1597-1607.
[49]Chen X, Fan H, Girshick R, et al. Improved baselines with momentum contrastive learning[J].arXivpreprint arXiv:2003.04297,2020.
[50]Chen T, Kornblith S, Swersky K, et al. Big self-supervised models are strong semi-supervisedlearners[J].Advancesinneuralinformationprocessingsystems,2020,33:22243-22255.
[51]Le-Khac P H, Healy G, Smeaton A F.Contrastive representation learning: A framework andreview[J/OL].IEEEAccess,2020,8:193907-193934.DOI:10.1109/ACCESS.2020.3031549.
[52]Yang Y, Kang C, Gou G, et al.Tls/ssl encrypted traffic classification with autoencoder andconvolutional neural network[C/OL]//2018 IEEE 20th International Conference on High Per-formance Computing and Communications;IEEE 16th International Conference on SmartCity;IEEE4thInternationalConferenceonDataScienceandSystems(HPCC/SmartCity/DSS).2018:362-369.DOI: 10.1109/HPCC/SmartCity/DSS.2018.00079.
[53]Wei J, Zou K. Eda: Easy data augmentation techniques for boosting performance on text clas-sificationtasks[J].ArXiv,2019, abs/1901.11196.
[54]Glorot X, Bordes A, Bengio Y.Deep sparse rectifier neural networks[C]//Proceedings of thefourteenthinternationalconferenceonartificialintelligenceandstatistics.JMLRWorkshopandConferenceProceedings, 2011:315-323.
[55]GutmannM,HyvärinenA.Noise-contrastiveestimation:Anewestimationprincipleforunnor-malizedstatisticalmodels[C]//Proceedingsofthethirteenthinternationalconferenceonartificialintelligenceandstatistics.JMLRWorkshopandConferenceProceedings,2010:297-304.
[56]LampingU,WarnickeE.Wiresharkuser’sguide[J].Interface,2004,4(6):1.
[57]KingmaDP,BaJ. Adam: Amethodforstochasticoptimization[J]. arXivpreprintarXiv:1412.6980,2014.
[58]LittlechildS C, OwenG.A simple expressionfor the shapley valuein a specialcase[J].Man-agementScience, 1973, 20(3):370-372.
[59]ZhangQs,ZhuSC.Visualinterpretabilityfordeeplearning:asurvey[J].FrontiersofInfor-mationTechnology& ElectronicEngineering, 2018, 19(1):27-39.
[60]Choo J, Liu S. Visual analytics for explainable deep learning[J/OL]. IEEE Computer GraphicsandApplications, 2018, 38(4):84-92.DOI: 10.1109/MCG.2018.042731661.
[61]WangT,IsolaP.Understandingcontrastiverepresentationlearningthroughalignmentanduni-formity on the hypersphere[C]//International Conference on Machine Learning. PMLR, 2020:9929-9939.
[62]Devlin J, Chang M W, Lee K, et al.Bert: Pre-training of deep bidirectional transformers forlanguageunderstanding[J].arXiv preprint arXiv:1810.04805,2018.
[63]LiuY,OttM,GoyalN,etal.Roberta:Arobustlyoptimizedbertpretrainingapproach[J].arXivpreprint arXiv:1907.11692,2019.
[64]Lan Z, Chen M, Goodman S, et al. Albert: A lite bert for self-supervised learning of languagerepresentations[J].arXiv preprint arXiv:1909.11942,2019.
[65]Yang Z, Dai Z, Yang Y, et al. Xlnet: Generalized autoregressive pretraining for language un-derstanding[J].Advancesinneural informationprocessingsystems,2019,32.
[66]Song K, Tan X, Qin T, et al.Mass: Masked sequence to sequence pre-training for languagegeneration[J].arXiv preprint arXiv:1905.02450,2019.
[67]Dong L, Yang N, Wang W, et al.Unified language model pre-training for natural languageunderstanding and generation[J].Advances in Neural Information Processing Systems, 2019,32.
[68]LinTY,GoyalP,GirshickR,etal.Focallossfordenseobjectdetection[C]//ProceedingsoftheIEEEinternational conference on computer vision.2017:2980-2988.
[69]PrecheltL.Earlystopping-butwhen?[M]//NeuralNetworks:Tricksofthetrade.Springer,1998:55-69.
[70]SrivastavaN,HintonG,KrizhevskyA,etal.Dropout:asimplewaytopreventneuralnetworksfromoverfitting[J].Thejournalofmachinelearningresearch,2014,15(1):1929-1958.
[71]GaoT,YaoX,ChenD.Simcse:Simplecontrastivelearningofsentenceembeddings[J].arXivpreprint arXiv:2104.08821,2021.
[72]Konečnỳ J, McMahan B, Ramage D. Federated optimization: Distributed optimization beyondthedatacenter[J].arXiv preprint arXiv:1511.03575,2015.
[73]McMahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networksfromdecentralizeddata[C]//Artificialintelligenceandstatistics.PMLR,2017:1273-1282.
[74]ZhaoY,LiM,LaiL,etal.Federatedlearningwithnon-iiddata[J].arXivpreprintarXiv:1806.00582,2018.
[75]LiX,HuangK,YangW,etal.Ontheconvergenceoffedavgonnon-iiddata[J].arXivpreprintarXiv:1907.02189,2019.
[76]WHDY.Fedavg[EB/OL].2022[2022-04-07].https://github.com/WHDY/FedAvg.
评论