吉林大学学报(工学版) ›› 2023, Vol. 53 ›› Issue (7): 2121-2126.doi: 10.13229/j.cnki.jdxbgxb.20220370

• 计算机科学与技术 • 上一篇    

基于深度神经网络的物联网安全态势自动辨识算法设计

刘鹏举1,2()   

  1. 1.武汉大学 国家网络安全学院,武汉 430072
    2.武汉大学 空天信息安全与可信计算教育部重点实验室,武汉 430072
  • 收稿日期:2022-04-21 出版日期:2023-07-01 发布日期:2023-07-20
  • 作者简介:刘鹏举(1997-),男,工程师,硕士. 研究方向:网络及信息安全,移动物联网安全.E-mail:849769803@qq.com
  • 基金资助:
    国家自然科学基金项目(62172308)

Design of automatic identification algorithm for Internet of Things security situation based on deep neural network

Peng-ju LIU1,2()   

  1. 1.School of Cyber Science and Engineering,Wuhan University,Wuhan 430072,China
    2.Key Laboratory of Aerospace Information Security and Trusted Computing of Ministry of Education,Wuhan University,Wuhan 430072,China
  • Received:2022-04-21 Online:2023-07-01 Published:2023-07-20

摘要:

针对网络未知的攻击威胁对物联网安全态势带来的影响,为了提升辨识效果,提出一种基于深度神经网络的物联网安全态势自动辨识算法。通过网络木马及DDos攻击分析物联网的安全威胁,获取物联网安全态势要素,通过建立病毒入侵的物联网安全状态分布模型,提取物联网安全态势特征,将深度神经网络与深度堆栈编辑器相结合,对提取的安全态势特征进行训练,利用最终训练结果判定物联网安全态势性能,完成物联网安全态势自动辨识,实现物联网安全态势自动辨识算法设计。实验结果表明,通过对该算法进行识别效果对比测试、召回率测试、F1值测试和识别运行时间测试,验证了该算法的精准度高、实用性强。

关键词: 深度神经网络, 物联网, 安全态势, 自动辨识

Abstract:

The unknown attack threat of the network will affect the security situation of the Internet of Things. In order to improve the identification effect, an automatic identification algorithm of the security situation of the Internet of Things based on deep neural network is proposed. Analyze the security threats of the Internet of Things through Trojan horse and DDoS attacks, obtain the security situation elements of the Internet of Things, extract the security situation characteristics of the Internet of Things by establishing the security state distribution model of the Internet of Things invaded by viruses, combine the deep neural network with the deep stack editor, train the extracted security situation characteristics, and use the final training results to determine the security situation performance of the Internet of Things, Complete the automatic identification of Internet of Things security situation and realize the design of automatic identification algorithm of Internet of Things security situation. The experimental results show that the algorithm has high accuracy and strong practicability through the comparison test of recognition effect, recall test, F1 value test and recognition running time test.

Key words: deep neural network, Internet of Things, security situation, automatic identification

中图分类号: 

  • TP393

图1

层次化物联网安全态势要素获取架构"

图2

基于深度神经网络的训练流程"

图3

识别准确率对比结果"

表1

三种方法的召回率对比测试"

物联网安全态势

数据集/个

不同方法的召回率/%
算法1算法2算法3
20098.993.293.6
40097.592.992.7
60097.491.691.5
80096.990.590.6
100096.589.389.7
120095.385.488.6

图4

F1值对比测试"

图5

识别运行时间测试"

1 边寒, 陈小红, 金芝, 等. 基于环境建模的物联网系统TAP规则生成方法[J]. 软件学报, 2021, 32(4): 934-952.
Bian Han, Chen Xiao-hong, Jin Zhi, et al. Approach to generating TAP rules in IoT systems based on environment modeling[J]. Journal of Software, 2021, 32(4): 934-952.
2 杨婷婷, 李志一, 赵冬泉.基于物联网大数据的城市降雨径流控制率分析[J]. 水电能源科学, 2020, 38(5): 15-17, 210.
Yang Ting-ting, Li Zhi-yi, Zhao Dong-quan. Analysis of urban rainfall and runoff control rate based on IoT big data[J]. Water Resources and Power, 2020, 38(5): 15-17, 210.
3 张帅钦, 张荣杰, 温旭东. 基于一维像选择双谱的神经网络识别算法[J]. 现代雷达, 2020, 42(4): 46-49.
Zhang Shuai-qin, Zhang Rong-jie, Wen Xu-dong. A neural network recognition algorithm based on one-dimensional image selection bispectrum[J]. Modern Radar, 2020, 42(4): 46-49.
4 唐作栋, 龚晓峰, 雒瑞森.一种小波特征与深度神经网络结合的信号制式识别算法[J]. 计算机工程与科学, 2020, 42(5): 902-909.
Tang Zuo-dong, Gong Xiao-feng, Luo Rui-sen. A signal system recognition algorithm combining wavelet features and deep neural networks[J]. Computer Engineering and Science, 2020, 42(5): 902-909.
5 苟泽中, 许华, 郑万泽, 等.基于半监督联合神经网络的调制识别算法[J]. 信号处理, 2020, 36(2): 168-176.
Gou Ze-zhong, Xu Hua, Zheng Wan-ze, et al. Semi-supervised joint neural network based recognition algorithm of modulation signal[J]. Journal of Signal Processing, 2020, 36(2): 168-176.
6 丑义凡, 易波, 王兴伟, 等. IPv6网络中基于MF-DL的DDoS攻击快速防御机制[J]. 计算机学报, 2021, 44(10): 2047-2060.
Yi-fan Chou, Yi Bo, Wang Xing-wei, et al. A rapid defense mechanism based on MF-DL for DDoS attack in IPv6 networks[J]. Chinese Journal of Computers, 2021, 44(10): 2047-2060.
7 张欣, 朱江.面向样本不平衡的网络安全态势要素获取[J]. 计算机工程与应用, 2022, 58(1): 134-142.
Zhang Xin, Zhu Jiang. Network security situation element acquisition for sample imbalance[J]. Computer Engineering and Applications, 2022, 58(1): 134-142.
8 牛祥.基于门限联合判别的同质网络入侵检测仿真[J]. 计算机仿真, 2020, 37(3): 309-313.
Niu Xiang. Simulation of homogeneous network intrusion detection based on threshold joint discrimination[J]. Computer Simulation, 2020, 37(3): 309-313.
9 景惠甜, 韩丽, 高志宇. 基于卷积神经网络特征提取的风电功率爬坡预测[J]. 电力系统自动化, 2021, 45(4): 98-105.
Jing Hui-tian, Han Li, Gao Zhi-yu. Wind power ramp prediction based on feature extraction of convolutional neural network[J]. Automation of Electric Power Systems, 2021, 45(4): 98-105.
10 曲岳晗, 赵洪山, 马利波, 等. 多深度神经网络综合的电力变压器故障识别方法[J]. 中国电机工程学报, 2021, 41(23): 8223-8231.
Qu Yue-han, Zhao Hong-shan, Ma Li-bo, et al. Multi-depth neural network synthesis method for power transformer fault identification[J]. Proceedings of the CSEE, 2021, 41(23): 8223-8231.
[1] 冀汶莉,田忠,柴敬,张丁丁,王斌. 多属性融合分布式光纤导水裂隙带高度预测方法[J]. 吉林大学学报(工学版), 2023, 53(4): 1200-1210.
[2] 宋现敏,杨舒天,刘明鑫,李志慧. 站点间公交行程时间波动特性及预测方法[J]. 吉林大学学报(工学版), 2022, 52(8): 1792-1799.
[3] 孙东明,胡亮,邢永恒,王峰. 基于文本融合的物联网触发动作编程模式服务推荐方法[J]. 吉林大学学报(工学版), 2021, 51(6): 2182-2189.
[4] 陈红松,陈京九. 基于统计的物联网分布式拒绝服务攻击检测[J]. 吉林大学学报(工学版), 2020, 50(5): 1894-1904.
[5] 傅文博, 张杰, 陈永乐. 物联网环境下抵抗路由欺骗攻击的网络拓扑发现算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[6] 胡冠宇, 乔佩利. 混沌协方差矩阵自适应进化策略优化算法[J]. 吉林大学学报(工学版), 2017, 47(3): 937-943.
[7] 胡冠宇, 乔佩利. 基于云群的高维差分进化算法及其在网络安全态势预测上的应用[J]. 吉林大学学报(工学版), 2016, 46(2): 568-577.
[8] 李抵非,田地,胡雄伟. 基于深度学习的中文标准文献语言模型[J]. 吉林大学学报(工学版), 2015, 45(2): 596-599.
[9] 刘效武, 王慧强, 吕宏武, 安述照. 基于融合的网络安全态势量化感知[J]. 吉林大学学报(工学版), 2013, 43(06): 1650-1657.
[10] 王堃, 于悦, 张玉华, 郭篁, 王琳琳. 面向物联网应用平台的Socket设计与优化[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 290-294.
[11] 吕超, 刘爽, 王世明. 智能电网管理服务系统集成框架[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 246-250.
[12] 田晶晶, 李世武, 苏建, 王琳虹, 孙文财, 陈璐. 基于位移传感器的汽车超载动态监测预警系统[J]. , 2012, (06): 1475-1480.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!