典型文献
Length matters:Scalable fast encrypted internet traffic service classification based on multiple protocol data unit length sequence with composite deep learning
文献摘要：
As an essential function of encrypted Internet traffic analysis,encrypted traffic service classification can support both coarse-grained network service traffic management and security supervision.However,the traditional plaintext-based Deep Packet Inspection(DPI)method cannot be applied to such a classification.Moreover,ma-chine learning-based existing methods encounter two problems during feature selection:complex feature overcost processing and Transport Layer Security(TLS)version discrepancy.In this paper,we consider differences between encryption network protocol stacks and propose a composite deep learning-based method in multiprotocol en-vironments using a sliding multiple Protocol Data Unit(multiPDU)length sequence as features by fully utilizing the Markov property in a multiPDU length sequence and maintaining suitability with a TLS-1.3 environment.Control experiments show that both Length-Sensitive(LS)composite deep learning model using a capsule neural network and LS-long short time memory achieve satisfactory effectiveness in F1-score and performance.Owing to faster feature extraction,our method is suitable for actual network environments and superior to state-of-the-art methods.
文献关键词：
中图分类号：
作者姓名：
Zihan Chen;Guang Cheng;Ziheng Xu;Shuyi Guo;Yuyang Zhou;Yuyu Zhao
作者机构：
School of Cyber Science and Engineering,Southeast University,Nanjing,211189,China;Key Laboratory of Computer Network and Information Integration,Ministry of Education,Nanjing,211189,China;Purple Mountain Laboratories,Nanjing,211111,China
文献出处：
引用格式：
[1]Zihan Chen;Guang Cheng;Ziheng Xu;Shuyi Guo;Yuyang Zhou;Yuyu Zhao-.Length matters:Scalable fast encrypted internet traffic service classification based on multiple protocol data unit length sequence with composite deep learning)[J].数字通信与网络（英文）,2022(03):289-302
A类：
overcost,multiprotocol,multiPDU
B类：
Length,matters,Scalable,encrypted,internet,traffic,service,classification,multiple,data,unit,length,sequence,composite,deep,learning,essential,function,Internet,analysis,support,both,coarse,grained,network,management,security,supervision,However,traditional,plaintext,Deep,Packet,Inspection,DPI,cannot,applied,such,Moreover,chine,existing,methods,encounter,problems,during,selection,complex,processing,Transport,Layer,Security,TLS,version,discrepancy,this,paper,consider,differences,between,encryption,stacks,propose,using,sliding,Protocol,Data,Unit,features,by,fully,utilizing,Markov,property,maintaining,suitability,Control,experiments,show,that,Sensitive,model,capsule,neural,long,short,memory,achieve,satisfactory,effectiveness,score,performance,Owing,faster,extraction,our,suitable,actual,environments,superior,state,art
AB值：
0.590495
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
