|
|
论文:2020,Vol:38,Issue(5):1129-1137 |
|
|
引用本文： |
|
|
吕娜, 周家欣, 陈卓, 陈旿. 小训练样本条件下的机载网络流量识别方法[J]. 西北工业大学学报 |
|
|
LYU Na, ZHOU Jiaxin, CHEN Zhuo, CHEN Wu. Airborne Network Traffic Identification Method under Small Training Samples[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 小训练样本条件下的机载网络流量识别方法 |
|
| 吕娜1, 周家欣1, 陈卓1, 陈旿2 |
|
1. 空军工程大学 信息与导航学院, 陕西 西安 710077;
2. 西北工业大学 网络安全学院, 陕西 西安 710072 |
| 摘要: |
| 机载网络环境下，流量数据集获取成本高、难度大，且流量分布时间敏感度较高，导致基于机器学习的流量识别方法难以获得实际应用。针对该问题，提出了一种基于卷积神经网络的小流量样本条件下机载网络流量识别方法，首先基于源领域完备数据集实现卷积神经网络初始模型的预训练，然后在目标领域数据集上，通过基于层冻结的卷积神经网络微调学习算法实现卷积神经网络的重训练，从而构造基于特征迁移的卷积神经网络（FRT-CNN）模型实现流量样本的线上分类。通过在实际机载网络流量数据集上的实验结果表明，所提方法可以在流量训练样本有限的条件下保证流量识别准确性，且分类性能相比于现有小样本学习方法有显著提升。 |
| 关键词:
流量识别
卷积神经网络
迁移学习
机载网络
|
|
| Airborne Network Traffic Identification Method under Small Training Samples |
|
| LYU Na1, ZHOU Jiaxin1, CHEN Zhuo1, CHEN Wu2 |
|
1. School of Information and Navigation, PLA Air Force Engineering University, Xi'an 710077, China;
2. School of Cybersecurity, Northwestern Polytechnical University, Xi'an 710072, China |
| Abstract: |
| Due to the high cost and difficulty of traffic data set acquisition and the high time sensitivity of traffic distribution, the machine learning-based traffic identification method is difficult to be applied in airborne network environment. Aiming at this problem, a method for airborne network traffic identification based on the convolutional neural network under small traffic samples is proposed. Firstly, the pre-training of the initial model for the convolutional neural network is implemented based on the complete data set in source domain, and then the retraining of the convolutional neural network is realized through the layer frozen based fine-tuning learning algorithm of convolutional neural network on the incomplete dataset in target domain, and the convolutional neural network model based feature representing transferring(FRT-CNN) is constructed to realize online traffic identification. The experiment results on the actual airborne network traffic dataset show that the proposed method can guarantee the accuracy of traffic identification under limited traffic samples, and the classification performance is significantly improved comparing with the existing small-sample learning methods. |
| Key words:
traffic identification
convolutional neural network
transfer learning
airborne network
|
|
| 收稿日期: 2019-11-20
修回日期:
|
| DOI: 10.1051/jnwpu/20203851129 |
| 基金项目: 陕西省重点研发计划（2017GY-069）资助 |
| 通讯作者: 周家欣(1994-),空军工程大学硕士研究生,主要从事军事航空通信研究。e-mail:531786065@qq.com
Email：531786065@qq.com |
| 作者简介: 吕娜(1970-),女,空军工程大学教授、博士,主要从事航空数据链、通信网络研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 吕娜 在本刊中的所有文章 |
| 周家欣 在本刊中的所有文章 |
| 陈卓 在本刊中的所有文章 |
| 陈旿 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 霍大军. 网络化集群作战研究[M]. 北京:国防大学出版社,2013 HUO Dajun. Operation of Network Swarm[M]. Beijing:National Defense University Press, 2013(in Chinese)
[2] 梁一鑫, 程光, 郭晓军. 机载网络体系结构及其协议栈研究进展[J]. 软件学报, 2016, 27(1):96-111 LIANG Yixin, CHENG Guang, GUO Xiaojun. Research Progress on Architecture and Protocol Stack of the Airborne Network[J]. Journal of Software, 2016, 27(1):96-111(in Chinese)
[3] NGUYEN T T T, ARMITAGE G. A Survey of Techniques for Internet Traffic Classification Using Machine Learning[J]. IEEE Communications Surveys & Tutorials, 2009, 10(4):56-76
[4] MOORE A W, ZUEV D. Internet Traffic Classification Using Bayesian Analysis Techniques[J]. ACM Sigmetrics Performance Evaluation Review, 2005, 33(1):50
[5] WU K, KE J. A Scheme of Real-Time Traffic Classification in Secure Access of Power Enterprise Based on Improved Naïve Bayesian Classification Algorithm[C]//IEEE International Conference on Software Engineering & Service Science, 2017
[6] 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 XU Peng, LIN Sen. Internet Traffic Classification Using C4.5 Decision Tree[J]. Journal of Software, 2009, 20(10):2692-2704(in Chinese)
[7] TONG Da. QU Y R. PRASANNA V K. Accelerating Decision Tree Based Traffic Classification on FPGA and Multicore Platforms[J]. IEEE Trans on Parallel & Distributed Systems, 2017, 28(11):3046-3059
[8] CAO Jie, FANG Zhiyi, QU Guannan, et al. An Accurate Traffic Classification Model Based on Support Vector Machines[J]. Networks, 2017, 27(1):e1962
[9] SUN Guanglu, CHEN Teng, SU Yangyang, et al. Internet Traffic Classification Based on Incremental Support Vector Machines[J]. Mobile Networks & Applications, 2018, 23(14):1-8
[10] WANG Wei, ZHU Ming, ZENG Xuewen. Malware Traffic Classification Using Convolutional Neural Network for Representation Learning[C]//2017 International Conference on Information Networking(ICOIN), 2017:712-717
[11] WANG Wei, ZHU Ming, WANG Jinlin, et al. End-to-End Encrypted Traffic Classification with One Dimensional Convolution Neural Networks[C]//2017 IEEE International Conference on Intelligence and Security Informatics(ISI), 2017
[12] 王勇, 周慧怡, 俸皓, 等. 基于深度卷积神经网络的网络流量分类方法[J]. 通信学报, 2018, 39(1):14-23 WANG Yong, ZHOU Huiyi, FENG Hao, et al. Network Traffic Classification Method Basing on CNN[J]. Journal on Communications, 2018, 39(1):14-23(in Chinese)
[13] PAN Sinno Jialin, YANG Qiang. A Survey on Transfer Learning[J]. IEEE Trans on Knowledge & Data Engineering, 2010, 22(10):1345-1359
[14] SHIN H C, ROTH H R, GAO M, et al. Deep Convolutional Neural Networks for Computer Aided Detection:CNN Architectures, Dataset Characteristics and Transfer Learning[J]. IEEE Trans on Medical Imaging, 2016, 1(1):1285-1298
[15] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6):1-23 ZHOU Feiyan, JIN Linpeng, DONG Jun. Review of Convolutional Neural Network[J]. Chinese Journal of Computers, 2017, 40(6):1-23(in Chinese)
[16] 李勤, 师维, 孙界平, 等. 基于神经网络的网络流量识别技术研究[J]. 四川大学学报, 2017, 54(5):959-964 LI Qin, SHI Wei, SUN Jieping, et al. The Research of Network Traffic Identification Based on Convolutional Neural Network[J]. Journal of Sichuan University, 2017, 54(5):959-964(in Chinese)
[17] SHARIF Razavian A, AZIZPOUR H, SULLIVAN J, et al. CNN Feature Off-the-Shelf:an Astounding Baseline for Recognition[C]//Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, UH, USA, 2014:806-813
[18] JASON Yosinski, JEFF Clune, YOSHUA Bengio, et al. How Transferable Are Features in Deep Neural Networks?[C]//Advances in Neural Information Processing System 27, Montreal, Canada, 2014:3320-3328 |
|
|
|
相关文献: |
|
|
1．吕娜, 周家欣, 冯煊, 陈柯帆, 陈旿.一种时效增强的机载网络流量识别方法[J]. 西北工业大学学报, 2020,38(2): 341-350 |
|
|
2．张飞, 闫杰.基于深度卷积神经网络的云分类算法[J]. 西北工业大学学报, 2020,38(4): 740-746 |
|
|
|
|
|
|
