基于机器学习的光纤窃听检测方法

doi:10.11959/j.issn.1000-0801.2020299

电信科学 ›› 2020, Vol. 36 ›› Issue (11): 61-67.doi: 10.11959/j.issn.1000-0801.2020299

基于机器学习的光纤窃听检测方法

陈孝莲¹,秦奕¹,张杰²,李亚杰²,宋浩鲲²,张会彬²

¹ 国网江苏省电力有限公司无锡供电分公司，江苏无锡 214000
² 北京邮电大学信息光子与光通信研究院，北京 100876

修回日期:2020-09-07 出版日期:2020-11-20 发布日期:2020-12-09
作者简介:陈孝莲（1977- ），女，国网江苏省电力有限公司无锡供电分公司高级工程师，主要研究方向为电力通信|秦奕（1979- ），男，国网江苏省电力有限公司无锡供电分公司高级工程师，主要研究方向为电力通信运维|张杰（1972- ），男，博士，北京邮电大学信息光子与光通信研究院院长、博士生导师，主要研究方向为安全光通信技术|李亚杰（1990- ），男，博士，北京邮电大学信息光子与光通信研究院在站博士后，主要研究方向为安全光通信技术|宋浩鲲（1996- ），女，北京邮电大学信息光子与光通信研究院博士生，主要研究方向为安全光通信技术|张会彬（1980- ），男，博士，北京邮电大学信息光子与光通信研究院讲师，主要研究方向为安全光通信技术
基金资助:
江苏省电力有限公司科技项目(J2019124)

Optical fiber eavesdropping detection method based on machine learning

Xiaolian CHEN¹,Yi QIN¹,Jie ZHANG²,Yajie LI²,Haokun SONG²,Huibin ZHANG²

¹ Wuxi Power Supply Company,State Grid JiangSu Electric Power Co.,Ltd.,Wuxi 214000,China
² State Key Laboratory of Information Photonics and Optical Communications,Beijing University of Posts and Telecommunications,Beijing 100876,China

Revised:2020-09-07 Online:2020-11-20 Published:2020-12-09
Supported by:
Science and Technology Project of Jiangsu Electric Power Co.,Ltd.(J2019124)

摘要/Abstract

摘要：

光纤窃听是信息安全的重大隐患之一，但其隐蔽性较高的特点导致筛查困难。针对通信网络中面临的光纤窃听问题，提出了基于机器学习的光纤窃听检测方法。首先基于窃听对传输物理层的影响，设计了 7 个维度的特征向量提取方法；其次通过实验，模拟窃听并收集特征向量，利用两种机器学习算法进行分类检测和模型优化。实验证明，神经网络分类算法的性能优于K近邻分类算法，其在10%分光窃听中可以实现98.1%的窃听识别率。

关键词: 窃听检测, 光纤窃听, 机器学习, 神经网络

Abstract:

Optical fiber eavesdropping is one of the major hidden dangers of power grid information security,but detection is difficult due to its high concealment.Aiming at the eavesdropping problems faced by communication networks,an optical fiber eavesdropping detection method based on machine learning was proposed.Firstly,seven-dimensions feature vector extraction method was designed based on the influence of eavesdropping on the physical layer of transmission.Then eavesdropping was simulated and experimental feature vectors were collected.Finally,two machine learning algorithms were used for classification detection and model optimization.Experiments show that the performance of the neural network classification is better than the K-nearest neighbor classification,and it can achieve 98.1% eavesdropping recognition rate in 10% splitting ratio eavesdropping.

Key words: eavesdropping detection, fiber eavesdropping, machine learning, neural network

中图分类号:

TP393

陈孝莲,秦奕,张杰,李亚杰,宋浩鲲,张会彬. 基于机器学习的光纤窃听检测方法[J]. 电信科学, 2020, 36(11): 61-67.

Xiaolian CHEN,Yi QIN,Jie ZHANG,Yajie LI,Haokun SONG,Huibin ZHANG. Optical fiber eavesdropping detection method based on machine learning[J]. Telecommunications Science, 2020, 36(11): 61-67.

图/表 5

参考文献 18

[1]	黄伟庆 . 国家秘密不能曝“光”[J]. 保密工作, 2015(5):50.
	HUANG W Q . State secrets cannot be exposed[J]. Confidential Work, 2015(5):50.
[2]	张睿汭 . 光纤通信网络窃听方法及防御措施[J]. 电信科学, 2012,28(11): 112-115.
	ZHANG R R . Fiber optic communication network eavesdropping methods and defensive measures[J]. Telecommunications Science, 2012,28(11): 112-115.
[3]	IQBAL M Z , FATHALLAH H , BELHADJ N . Optical fiber tapping:methods and precautions[C]// Proceedings of 8th International Conference on High-capacity Optical Networks and Emerging Technologies. Piscataway:IEEE Press, 2011: 164-168.
[4]	邹钟璐 . 基于否定选择算法的现场运维故障预测方法研究[J]. 电力信息与通信技术, 2019,17(9): 55-61.
	ZOU Z L . Research on fault prediction method for on-site operation and maintenance based on negative selection algorithms[J]. Electric Power ICT, 2019,17(9): 55-61.
[5]	侯晓凯, 李师谦, 王杰琼 ,等. 一种基于神经网络的网络设备故障预测系统[J]. 山东理工大学学报(自然科学版), 2014,28(6): 29-34.
	HOU X K , LI S Q , WANG J Q ,et al. Neural network fault prediction system in network equipment[J]. Journal of Shandong University of Technology (Natural Science Edition), 2014,28(6): 29-34.
[6]	彭昌东 . 光纤通信网络窃听方法与防御对策[J]. 计算机产品与流通, 2019(12):36.
	PENG C D . Fiber optic communication network eavesdropping methods and defensive countermeasures[J]. Computer Products and Distribution, 2019(12):36.
[7]	范雨辰, 郭才福, 林毅俊 ,等. 一种电力光纤实时检测系统设计[J]. 计算机时代, 2014(8): 14-16.
	FAN Y C , GUO C F , LIN Y J ,et al. Design of real-time monitoring system for electric power optical fiber[J]. Computer Era, 2014(8): 14-16.
[8]	IRUKULAPATI N V , MARSELLA , DOMENICO ,et al. Stochastic digital backpropagation with residual memory compensation[J]. Lightwave Technology, 2016,34(2): 566-572.
[9]	BORKOWSKI R , ZIBAR D , CABALLERO A ,et al. Stokes space-based optical modulation format recognition for digital coherent receivers[J]. IEEE Photonics Technology Letters, 2013,25(21): 2129-2132.
[10]	ISAUTIER P , PAN J , DESALVO R ,et al. Stokes space-based modulation format recognition for autonomous optical receivers[J]. Lightwave Technology, 2015,33(24): 5157-5163.
[11]	WU X , JARGON J , SKOOG R ,et al. Applications of artificial neural networks in optical performance monitoring[J]. Lightwave Technology, 2009,27(16): 3580-3589.
[12]	WU X , JARGON J , PARASCHIS L ,et al. ANN-based optical performance monitoring of QPSK signals using parameters derived from balanced-detected asynchronous diagrams[J]. IEEE Photonics Technology Letters, 2011,23(4): 248-250.
[13]	DONG Z , KHAN F , SUI Q ,et al. Optical performance monitoring:a review of current and future technologies[J]. Lightwave Technology, 2016,34(2): 525-543.
[14]	GONZALEZ N G , ZIBAR D , MONROY I T . Cognitive digital receiver for burst mode phase modulated radio over fiber links[C]// Proceedings of 6th European Conference and Exhibition on Optical Communication.[S.n:s]. 2010:(1): 23-25.
[15]	NAZARATHY M , KHURGIN J , WEIDENFELD R ,et al. Phased-array cancellation of nonlinear FWM in coherent OFDM dispersive multi-span links[J]. Optics Express, 2008,16(20): 15777-15810.
[16]	CHEN X , SHIEH W . Closed-form expressions for nonlinear transmission performance of densely spaced coherent optical OFDM systems[J]. Optics Express, 2010,18(18): 19039-19054.
[17]	LIPPMANN R . An introduction to computing with neural nets[J]. ASSP Magazine, 1987,4(2): 4-22.
[18]	邓大鹏, 盛兴, 廖晓闽 ,等. 基于LabVIEW的光纤安全监视预警系统的设计[J]. 光通信技术, 2011,35(10): 57-59.
	DENG D P , SHENG X , LIAO X M ,et al. Design of supervising and early-warning system for the safety of optical fiber based on LabVIEW platform[J]. Optical Communication Technology, 2011,35(10): 57-59.

基于机器学习的光纤窃听检测方法

Optical fiber eavesdropping detection method based on machine learning

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 18

相关文章 15

Metrics

推荐阅读 0

[1]	郭泽华, 朱昊文, 徐同文. 面向分布式机器学习的网络模态创新[J]. 电信科学, 2023, 39(6): 44-51.
[2]	刘思聪, 苏丹萍, 卫天阔, 王先耀. 基于多节点协作的鲁棒可见光智能定位[J]. 电信科学, 2023, 39(5): 28-41.
[3]	卢敏, 秦泽豪, 陈志辉, 张敏, 乐光学. 基于1D-Concatenate的信道估计DNN模型优化方法[J]. 电信科学, 2023, 39(4): 71-86.
[4]	刘雅琼, 吕哲, 赵亚飞, 寿国础. AI技术在卫星通信/互联网领域的应用综述[J]. 电信科学, 2023, 39(2): 10-24.
[5]	刘璐, 杨丹, 陈睿杰, 李嘉, 周熹. 基于KPCA-GA-BP神经网络的POI质量预测研究[J]. 电信科学, 2023, 39(1): 108-116.
[6]	章坚武, 安彦军, 邓黄燕. DNS攻击检测与安全防护研究综述[J]. 电信科学, 2022, 38(9): 1-17.
[7]	李奕江, 叶会标, 谢仁华, 楼佳丽, 庄丹娜, 李传煌. 基于图神经网络的网络性能智能预测[J]. 电信科学, 2022, 38(3): 143-157.
[8]	李攀攀, 谢正霞, 乐光学, 刘鑫. 基于深度学习的无线通信接收方法研究进展与趋势[J]. 电信科学, 2022, 38(2): 1-17.
[9]	赵海波, 相志军, 肖林松. 基于异构数据的电力短期负荷大数据预测方案[J]. 电信科学, 2022, 38(12): 103-111.
[10]	陈靓, 钱亚冠, 何志强, 关晓惠, 王滨, 王星. 深度卷积神经网络的柔性剪枝策略[J]. 电信科学, 2022, 38(1): 83-94.
[11]	周志超, 冯毅, 夏小涵, 冯瑜瑶, 蔡超, 邱佳慧, 杨立辉, 乌云霄. 基于移动蜂窝网的机器学习室外指纹定位方案[J]. 电信科学, 2021, 37(8): 85-95.
[12]	赵进, 杨小军. 基于GRW和FastText模型的电信用户投诉文本分类应用[J]. 电信科学, 2021, 37(6): 125-131.
[13]	孙姝君, 彭盛亮, 姚育东, 杨喜. 基于深度学习的调制识别综述[J]. 电信科学, 2021, 37(5): 82-90.
[14]	陈向荣. 基于多层感知机模型的天线方位角诊断[J]. 电信科学, 2021, 37(4): 90-96.
[15]	刘子豪, 贾小军, 张素兰, 徐志玲, 张俊. 一种融合MeanShift聚类分析和卷积神经网络的Vibe++背景分割方法[J]. 电信科学, 2021, 37(3): 133-145.