[논문]Network Traffic Classification Based on Deep Learning

Li, Junwei; Pan, Zhisong

doi:10.3837/tiis.2020.11.001

Network Traffic Classification Based on Deep Learning 원문보기

KSII Transactions on internet and information systems : TIIS, v.14 no.11, 2020년, pp.4246 - 4267

Li, Junwei (Institute of Command Control Engineering, Army Engineering University) , Pan, Zhisong (Institute of Command Control Engineering, Army Engineering University)

Abstract ▼ AI-Helper

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

주제어

표/그림 (15)

그림 Fig. 1. Number of Internet users and Internet penetration
표 Table1. Traffic classification objects
그림 Fig. 2. Research progress of network traffic classification
그림 Fig. 3. Comparison traffic classification based on machine learning with deep learning
그림 Fig. 4. AE model
그림 Fig. 5. SAE model
그림 Fig. 6. Structure of 2D-CNN
그림 Fig. 7. Structure of 1D-CNN
그림 Fig. 8. Structure of 3D-CNN
표 Table 2. Comparison of classification based on CNN
그림 Fig. 9. Structure of recurrent neural network
그림 Fig. 10. Traffic classification based on LSTM
그림 Fig. 11. Structure of DBN
표 Table 3. Comparison of Classification Methods Based on Various Types of Deep Learning
그림 Fig. 12. Comparison of Classification Method Based on Deep Learning with Others

AI 본문요약
AI-Helper

제안 방법

The main idea is to convert the packet header data of traffic bytes into pictures, and add the dimension of time characteristics to form three-dimensional data as input, which is equivalent to converting traffic data into multi-frame gray images in video processing, splicing one frame to one large image, and learning the characteristics of these large images by using 3D-CNN model to improve learning efficiency.
We analyzed the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network and long short-term memory network from their respective principles, preprocessing methods, using models, technical implementation and classification results. Moreover, the traffic classification based on deep learning is compared with methods based on port number, deep packets detection and machine learning.

대상 데이터

The data set contains a total of 300 thousand pieces of data collected from the real data of 360 company network.

성능/효과

(3) Unsupervised and semi-supervised methods are used for classification. It is good to train deep neural network with labeled data for classification, but in reality, labeled data is difficult to obtain.
As can be seen more intuitively from Fig. 12, the network traffic classification method based on deep learning can adopt the offline-training and online-identification method to further reduce the computational complexity, which can improve the efficiency of real-time classification. It is the most commonly used method for traffic classification at present.
Moreover, the traffic classification based on deep learning is compared with methods based on port number, deep packets detection and machine learning. Finally, the future research direction and trend of network traffic classification based on deep learning are prospected.
The research of network traffic classification has entered a new stage of deep learning, and has made great progress. However, it also faces some problems and challenges, such as the lack of open data sets and the need to further improve the performance of the algorithm. The next step is to do further research in the following aspects.
Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network and long short-term memory network from their respective principles, preprocessing methods, using models, technical implementation and classification results. Moreover, the traffic classification based on deep learning is compared with methods based on port number, deep packets detection and machine learning. Finally, the future research direction and trend of network traffic classification based on deep learning are prospected.
With the continuous progress of deep learning, network traffic classification is full of opportunities and challenges, and there is still much room for improvement. It is hoped that we can provide a more comprehensive understanding of network traffic classification based on deep learning and reference for network planning, network management and network security, and expect that traffic classification can make further progress.
With the increasing complexity of network traffic, traffic classification becomes more and more important. We analyzed the research background and progress of network traffic classification.

후속연구

With the continuous progress of deep learning, network traffic classification is full of opportunities and challenges, and there is still much room for improvement. It is hoped that we can provide a more comprehensive understanding of network traffic classification based on deep learning and reference for network planning, network management and network security, and expect that traffic classification can make further progress.

참고문헌 (53)

China Internet Network Information Center, "Internet usage," Statistical Report on the Development of Internet in China, pp. 17-18, February 2019.
Aceto G, Ciuonzo D, Montieri A, "Mobile encrypted traffic classification using deep learning," in Proc. of 2018 Network Traffic Measurement and Analysis Conference (TMA), pp. 1-8, 2018.
Wang W, Zhu M, Zeng X, "Malware traffic classification using convolutional neural network for representation learning," in Proc. of 2017 International Conference on Information Networking (ICOIN), pp. 712-717, 2017.
Ducange P, Mannara G, Marcelloni F, "A novel approach for internet traffic classification based on multi-objective evolutionary fuzzy classifiers," in Proc. of 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE, pp. 1-6, 2017.
Shone N, Ngoc T N, Phai V D, "A deep learning approach to network intrusion detection," IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 2, no.1, pp. 41-50, 2018.

상세보기
Sun G, Liang L, Chen T, Xiao F, Fang L, "Network traffic classification based on transfer learning," Computers & electrical engineering, vol. 69, pp. 920-927, 2018.

상세보기
Moore A W, Zuev D, "Discriminators for use in Flow-based classification," Technical Report IRC-TR-04-028, Intel Research, Cambridge, 2005.
Zhang J, Chen X, Xiang Y, "Robust network traffic classification," IEEE/ACM Transactions on Networking (TON), vol. 23, no. 4, pp. 1257-1270, 2015.

상세보기
He G, Yang M, Luo J, "A novel application classification attack against Tor," Concurrency and Computation: Practice and Experience, vol. 27, no.18, pp. 5640-5661, 2015.

상세보기
McGaughey D, Semeniuk D, Smith R, "A systematic approach of feature selection for encrypted network traffic classification," in Proc. of the 2018 Annual IEEE International Systems Conference, Piscataway, NJ: IEEE, pp. 1- 8, 2018.
Sarkar A, Dasgupta S, Naskar S K, "Says Who? Deep Learning Models for Joint Speech Recognition, Segmentation and Diarization," in Proc. of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, pp. 5229-5233, 2018.
Lopez-Martin M, Carro B, Sanchez-Esguevillas A, "Network Traffic Classifier with Convolutional and Recurrent Neural Networks for Internet of Things," IEEE Access, vol. 5, pp. 18042-18050, 2017.

상세보기
Wang W, "HAST-IDS: Learning Hierarchical Spatial-Temporal Features Using Deep Neural Networks to Improve Intrusion Detection," IEEE Access, vol. 6, pp. 1792-1806, 2018.

상세보기
Wu K, Chen Z, Li W, "A Novel Intrusion Detection Model for a Massive Network Using Convolutional Neural Networks," IEEE Access, vol. 6, pp. 50850-50859, 2018.

상세보기
Adie H T R, Pradana I A, "Parallel Computing Accelerated Image Inpainting using GPU CUDA, Theano and Tensorflow," in Proc. of 2018 10th International Conference on Information Technology and Electrical Engineering (ICITEE), Kuta, pp. 621-625, 2018.
Perera P, Tian Y C, Fidge C, "A comparison of supervised machine learning algorithms for classification of communications network traffic," in Proc. of International Conference on Neural Information Processing. Springer, Cham, pp. 445-454, 2017.
Zhang L , Cui Y, "Application of Machine Learning in Cyberspace Security Research," Chinese Journal of Computers, vol. 41, no 9, pp. 1943-1975, 2018.
Ge Y F, Peng F , Feng X X, "Homology Analysis of Malicious Code Based on Dynamic BP Neural Network," Journal of Chinese Computer Systems, vol. 37, no. 11,pp. 2527-2531, 2016.
HE H, "A network traffic classification method using support vector machine with feature weighted-degree," Journal of Digital Information Management, vol. 15, no. 5, pp. 76-83, 2017.
Moore A W, Zuev D, "Internet traffic classification using Bayesian analysis techniques," ACM SIGMETRICS Performance Evaluation Review, vol. 33, no. 1, 2005.
KONG L, HUANG G, WU K, "Identification of abnormal network traffic using support vector machine," in Proc. of the 2017 18th International Conference on Parallel and Distributed Computing, Applications and Technologies, Piscataway, NJ: IEEE, pp. 288-292, 2017.
Wang R, Feng D G, "Feature extraction and detection method of malicious code based on semantics," Journal of Software, vol. 23, no. 2, pp. 378-393, 2012.

상세보기
Vu L, Bui C T, Nguyen Q U, "A deep learning based method for handling imbalanced problem in network traffic classification," in Proc. of the Eighth International Symposium on Information and Communication Technology, ACM, pp. 333-339, 2017.
Rao Z, Niu W, Zhang X S, "Tor anonymous traffic identification based on gravitational clustering," Peer-to-Peer Networking and Applications, vol. 11, pp. 592-601, 2018.

상세보기
Velan P, Cermak M, Celeda P, "A survey of methods for encrypted traffic classification and analysis," International Journal of Network Management, vol. 25, no.5, pp. 355-374, 2015.

상세보기
Deng Z, Qian G, Chen Z, "Identifying Tor Anonymous Traffic Based on Gravitational Clustering Analysis," in Proc. of International Conference on Intelligent Human-Machine Systems and Cybernetics, IEEE, pp. 79-83, 2017.
Song L, Chang L, "Application of mutation particle swarm optimization BP neural network in malicious code detection," Journal of Intelligent Systems, vol. 8, no. 6, pp. 558-563, 2013.
Carela-Espanol V, Barlet-Ros P, Mula-Valls O, "An autonomic traffic classification system for network operation and management," Journal of Network and Systems Management, vol. 23, no. 3, pp. 401-419, 2015.

상세보기
Liu J, Zheng C, Guo L, "Understanding the Network Traffic Constraints for Deep Packet Inspection by Passive Measurement," in Proc. of 2018 3rd International Conference on Information Systems Engineering (ICISE), IEEE, pp. 26-32, 2018.
Ho T L, Cho S J, Oh S R, "Parallel multiple pattern matching schemes based on cuckoo filter for deep packet inspection on graphics processing units," IET Information Security, vol. 12, no. 4, pp. 381-388, 2018.

상세보기
Araujo I M, Natalino C, Santana A L, "Accelerating VNF-based Deep Packet Inspection with the use of GPUs," in Proc. of 2018 20th International Conference on Transparent Optical Networks (ICTON), IEEE, pp. 1-4, 2018.
Sivaprasad A, Ghawalkar N, Hodge S, "Machine learning based traffic classification using statistical analysis," Int. J. Recent Innov. Trends Comput. Commun., vol. 6, no. 3, pp. 187-191, 2018.
Krizhevsky A, Sutskever I, Hinton G E, "ImageNet classification with deep convolutional neural networks," in Proc. of International Conference on Neural Information Processing Systems, Curran Associates Inc., pp. 1097-1105, 2012.
Deshpande P, Sharma S C, Peddoju S K, "HIDS: A host based intrusion detection system for cloud computing environment," International Journal of System Assurance Engineering and Management, vol. 9, no. 3, pp. 567-576, 2018.

상세보기
LeCun Y, Bengio Y, Hinton G, "Deep learning," Nature, no. 521, pp. 436-444, 2015.
Tongaonkar A, Torres R, Iliofotou M, "Towards self-adaptive network traffic classification," Computer Communications, vol. 56, pp. 35-46, 2015.

상세보기
Amaral P, Dinis J, Pinto P, "Machine learning in software defined networks: Data collection and traffic classification," in Proc. of 2016 IEEE 24th International Conference on Network Protocols (ICNP), IEEE, pp. 1-5, 2016.
Ertam F, Avci E, "A new approach for internet traffic classification: GA-WK-ELM," Measurement, vol. 95, pp.135-142, 2017.

상세보기
Zhu Z, Liang D, Zhang S, "Traffic-sign detection and classification in the wild," in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2110-2118, 2016.
Aceto G, Ciuonzo D, Montieri A, "Traffic classification of mobile apps through multi-classification," in Proc. of GLOBECOM 2017-2017 IEEE Global Communications Conference, IEEE, pp. 1-6, 2017.
Dong Y, Zhao J, Jin J, "Novel feature selection and classification of Internet video traffic based on a hierarchical scheme," Computer Networks, vol. 119, pp. 102-111, 2017.

상세보기
Avci O, Abdeljaber O, Kiranyaz S, "Structural damage detection in real time: implementation of 1D convolutional neural networks for SHM applications," Structural Health Monitoring & Damage Detection, Springer, Cham, vol. 7, pp. 49-54, 2017.
Ran J, Kong X C, "A Self-adaptive Traffic Classification System with Unknown Flow Detection," in Proc. of 3rd IEEE International Conference on Computer and Communications, IEEE, pp. 1215-1220, 2017.
Ran J, Chen Y, Li S, "Three-dimensional Convolutional Neural Network based Traffic Classification for Wireless Communications," in Proc. of 2018 IEEE Global Conference on Signal and Information Processing (Global SIP), Anaheim, CA, USA, pp. 624-627, 2018.
Stevanovic M, Pedersen J M, "An analysis of network traffic classification for botnet detection," in Proc. of 2015 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA), IEEE, pp. 1-8, 2015.
Gomez S E, Martinez B C, Sanchez-Esguevillas A J, "Ensemble network traffic classification: Algorithm comparison and novel ensemble scheme proposal," Computer Networks, vol. 127, pp. 68-80, 2017.

상세보기
Hochst J, Baumgartner L, Hollick M, "Unsupervised traffic flow classification using a neural autoencoder," in Proc. of 2017 IEEE 42nd Conference on Local Computer Networks (LCN), IEEE, pp. 523-526, 2017.
Karim F, Majumdar S, Darabi H, "Multivariate lstm-fcns for time series classification," Neural Networks, vol. 116, pp. 237-245, 2019.

상세보기
Kim T Y, Cho S B, "Web traffic anomaly detection using C-LSTM neural networks," Expert Systems with Applications, vol. 106, pp. 66-76, 2018.

상세보기
Zou Z, Ge J, Zheng H, "Encrypted Traffic Classification with a Convolutional Long Short-Term Memory Neural Network," in Proc. of 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), IEEE, pp. 329-334, 2018.
Hinton G E, Salakhutdinov R R, "Reducing the dimensionality of data with neural networks," science, vol. 313, no. 5786, pp. 504-507, 2006.

상세보기
Shao H, Tang L, Dong L, "A Research of Network Applications Classification Based on Deep Learning," in Proc. of International Conference on Machine Learning and Intelligent Communications. Springer, Cham, pp. 13-21, 2018.
Taheri R, Javidan R, Shojafar M, "On Defending Against Label Flipping Attacks on Malware Detection Systems," Neural Computing and Applications, vol. 32, pp. 14781-14800, 2020.

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증