计算机科学 ›› 2021, Vol. 48 ›› Issue (12): 349-356.doi: 10.11896/jsjkx.210400227

• 信息安全 • 上一篇    下一篇

基于时间因子和复合CNN结构的网络安全态势评估

赵冬梅1,2, 宋会倩1, 张红斌3   

  1. 1 河北师范大学计算机与网络空间安全学院 石家庄050024
    2 河北师范大学河北省网络与信息安全重点实验室 石家庄050024
    3 河北科技大学信息科学与工程学院 石家庄050018
  • 收稿日期:2021-04-21 修回日期:2021-09-05 出版日期:2021-12-15 发布日期:2021-11-26
  • 通讯作者: 赵冬梅(zhaodongmei666@126.com)
  • 基金资助:
    国家自然科学基金(61672206);中央引导地方科技发展资金项目(216Z0701G);河北省重点研发计划基金资助项目(20310701D);河北省自然科学基金(F2019205163)

Network Security Situation Based on Time Factor and Composite CNN Structure

ZHAO Dong-mei1,2, SONG Hui-qian1, ZHANG Hong-bin3   

  1. 1 College of Computer and Cyber Security,Hebei Normal University,Shijiazhuang 050024,China
    2 Hebei Key Laboratory of Network and Information Security,Hebei Normal University,Shijiazhuang 050024,China
    3 School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,China
  • Received:2021-04-21 Revised:2021-09-05 Online:2021-12-15 Published:2021-11-26
  • About author:ZHAO Dong-mei,born in 1966,Ph.D,professor,Ph.D supervisor,is a senior member of China Computer Federation.Her main research interests include network information security and computer application.
  • Supported by:
    National Natural Science Foundation of China(61672206),Central Guide Local Science and Technology Development Fund Project(216Z0701G), Key Research and Development Program of Hebei Province(20310701D) and Natural Science Foundation of Hebei Province(F2019205163).

摘要: 为了解决传统的网络安全态势感知研究方法在网络信息复杂情况下准确率不高等缺陷,文中结合深度学习,提出了一种基于时间因子和复合CNN结构的网络安全态势评估模型,将卷积分解技术和深度可分离技术相结合,形成4层串联复合最优单元结构;将一维网络数据转换为二维矩阵,以灰度值的形式载入神经网络模型,从而有效发挥卷积神经网络的优势。为充分利用数据间的时序关系,引入时间因子形成融合数据,使网络同时学习具备时序关系的原始数据和融合数据,增强模型的特征提取能力,同时利用时间因子和点卷积建立时序数据的空间映射,提高模型结构的完整性。实验结果证明,所提模型在两个数据集上的准确率分别达到了92.89%和92.60%,相比随机森林和LSTM算法提升了2%~6%。

关键词: 态势感知, 卷积网络, 时间因子, 深度可分离卷积, 卷积分解

Abstract: In order to solve the problem of low accuracy of traditional network security situation awareness research methods in the case of complex network information,combined with deep learning,this paper proposes a network security situation assessment model based on time factor and composite CNN structure,which combines volume integral solution technology and deep separable technology to form a four layer series composite optimal unit structure.The one-dimensional network data are transformed into two-dimensional matrix and loaded into the neural network model in the form of gray value,so as to give full play to the advantages of convolution neural network.In order to make full use of the time-series relationship between data,time factor is introduced to form fusion data,which makes the network to learn the original data and fusion data with time-series relationship at the same time,the feature extraction ability of the model is increased,the spatial mapping of time-series data is established by using time factor and point convolution,and the integrity of the model structure is increased.Experimental results show that the accuracy of the proposed model on two datasets is 92.89% and 92.60% respectively,which is 2%~6% higher than randomfo-rest and LSTM algorithm.

Key words: Situational awareness, CNN, Time factor, Depthwise separable convolution, Convolution decomposition

中图分类号: 

  • TP393
[1]ENDSLEY M R.Toward a Theory of Situation Awareness in Dynamic Systems[J].Human Actors:The Journal of the Human Factors and Ergonomics Society,1995,37(1):32-64.
[2]BASS T.Multisensor Data Fusion for Next Generation Distributed Intrusion Detection Systems [C]//1999 Proceedings of the Iris National Symposium on Sensor & Data Fusion.1999:24-27.
[3]LIU X W,YU J G,LV W F,et al.Network security situation:from awareness to awareness-control[J].Journal of Network and Computer Applications,2019,139:15-30.
[4]ZHENG W.Research on situation awareness of network security assessment based on dempster-shafer[J].MATEC Web of Conferences,2020,309(10):02004.
[5]SUN W X.Pso and Svm for Network Security Situation Prediction[J].Computer Applications and Software,2019,36(6):308-316.
[6]LIN W N,CHEN M Z,ZHAN Y Q,et al.Research on an Intrusion Detection Algorithm Based on PCA and Random-forest Classification[J].Netinfo Security,2017(11):50-54.
[7]SHEN L,WEN Z C.Network security situation prediction in the cloud environment based on grey neural network[J].Journal of Computational Methods in Sciences and Engineering,2019,19(1):153-167.
[8]LIU J W,LIU J J,LU Y L,et al.Application of game theory in network security situation awareness[J].Journal of Computer Applications,2017,37(S2):48-51.
[9]ALAOUI I E,GAHI Y.Network Security Strategies in Big Data Context[J].Procedia Computer Science,2020,175:730-736.
[10]WANG Z J,CHEN L,SONG S Y,et al.Automatic cyber security risk assessment based on fuzzy fractional ordinary differential equations[J].Alexandria Engineering Journal,2020,59(4):2725-2731.
[11]DO C T,TRAN N H,HONG C,et al.Game Theory for Cyber Security and Privacy[J].ACM Computing Surveys,2017,50(2):1-37.
[12]BALAJ S,JULIE E G,ROBINSON Y H,et al.Design of a security-aware routing scheme in Mobile Ad-hoc Network using repeated game model[J].Computer Standards & Interfaces,2019,66(OCT):103358.1-103358.10.
[13]ZHAO D M,LIU J X.Study on network security situation awareness based on particle swarm optimization algorithm[J].Computers & Industrial Engineering,2018,125:764-775.
[14]LI S,ZHAO D M.LSTM-based method for comprehension and evaluation of network security situation[C]//2019 18th IEEE International Conference on Trust,Security and Privacy in Computing and Communications/13th IEEE International Confe-rence on Big Data Science and Engineering (TrustCom/BigDataSE).IEEE,2019:723-728.
[15]CHEN J G,QI Z H,CHEN T F.Network security situation awareness based on RBF neural networks[J].Journal of Nanjing University of Posts and Telecommunications(Natural Scien-ce Edition),2019,39(4):88-95.
[16]CHEN H S,CHEN J J.Recurrent Neural Networks Based Wireless Network Intrusion Detection and Classification Model Construction and Optimization[J].Journal of Electronics & Information Technology,2019,41(6):1427-1433.
[17]DEMIR F,SENGUR A,BAJAJ V.Convolutional neural net- works based efficient approach for classification of lung diseases[J].Health Information Science and Systems,2020,8(1):1-8.
[18]SYDNEY M K,SUN Y X.A deep learning method with wrapper based feature extraction for wireless intrusion detection system[J].Computers &Security,2020,92:101752.1-101752.15.
[1] 龚浩田, 张萌. 基于关键点检测的无锚框轻量级目标检测算法[J]. 计算机科学, 2021, 48(8): 106-110.
[2] 邢豪, 李明. 基于3D CNNS的深度伪造视频篡改检测[J]. 计算机科学, 2021, 48(7): 86-92.
[3] 宋龙泽, 万怀宇, 郭晟楠, 林友芳. 面向出租车空载时间预测的多任务时空图卷积网络[J]. 计算机科学, 2021, 48(7): 112-117.
[4] 卿来云, 张建功, 苗军. 在线异常事件检测的时序建模[J]. 计算机科学, 2021, 48(7): 206-212.
[5] 程思伟, 葛唯益, 王羽, 徐建. BGCN:基于BERT和图卷积网络的触发词检测[J]. 计算机科学, 2021, 48(7): 292-298.
[6] 和青芳, 王慧, 程光. 自适应小数据集乳腺癌病理组织分类研究[J]. 计算机科学, 2021, 48(6A): 67-73.
[7] 宋元隆, 吕光宏, 王桂芝, 贾吾财. 基于图卷积神经网络的SDN网络流量预测[J]. 计算机科学, 2021, 48(6A): 392-397.
[8] 唐亮, 李飞. 基于决策树的车联网安全态势预测模型研究[J]. 计算机科学, 2021, 48(6A): 514-517.
[9] 王丽芳, 王蕊芳, 蔺素珍, 秦品乐, 高媛, 张晋. 基于双残差超密集网络的多模态医学图像融合[J]. 计算机科学, 2021, 48(2): 160-166.
[10] 吕明琪, 洪照雄, 陈铁明. 一种融合时空关联与社会事件的交通流预测方法[J]. 计算机科学, 2021, 48(2): 264-270.
[11] 张慧. 基于深度卷积网络的多错误定位方法[J]. 计算机科学, 2021, 48(11A): 88-92.
[12] 叶松涛, 周扬正, 范红杰, 陈正雷. 融合因果关系和时空图卷积网络的人体动作识别[J]. 计算机科学, 2021, 48(11A): 130-135.
[13] 罗婷瑞, 贾建, 张瑞. 基于可调Q因子小波变换和迁移学习的癫痫脑电信号检测[J]. 计算机科学, 2020, 47(7): 199-205.
[14] 蒋宗礼, 李苗苗, 张津丽. 基于融合元路径图卷积的异质网络表示学习[J]. 计算机科学, 2020, 47(7): 231-235.
[15] 李欣, 段詠程. 基于改进隐马尔可夫模型的网络安全态势评估方法[J]. 计算机科学, 2020, 47(7): 287-291.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 周剑云,王丽珍,杨增芳. 基于加权欧氏距离的空间Co-location模式挖掘算法研究[J]. 计算机科学, 2014, 41(Z6): 425 -428 .
[2] 朱英宏,李俊山,杨威,杨亚威,朱艺娟. 异源图像特征点边缘描述与匹配[J]. 计算机科学, 2013, 40(7): 277 -279 .
[3] 杜威, 丁世飞. 多智能体强化学习综述[J]. 计算机科学, 2019, 46(8): 1 -8 .
[4] 王岩, 罗倩, 邓辉. 基于变分贝叶斯的轴承故障诊断方法[J]. 计算机科学, 2019, 46(11): 323 -327 .
[5] 胡昕彤, 沙朝锋, 刘艳君. 基于随机投影和主成分分析的网络嵌入后处理算法[J]. 计算机科学, 2021, 48(5): 124 -129 .
[6] 潘孝勤, 芦天亮, 杜彦辉, 仝鑫. 基于深度学习的语音合成与转换技术综述[J]. 计算机科学, 2021, 48(8): 200 -208 .
[7] 王俊, 王修来, 庞威, 赵鸿飞. 面向科技前瞻预测的大数据治理研究[J]. 计算机科学, 2021, 48(9): 36 -42 .
[8] 余力, 杜启翰, 岳博妍, 向君瑶, 徐冠宇, 冷友方. 基于强化学习的推荐研究综述[J]. 计算机科学, 2021, 48(10): 1 -18 .
[9] 王梓强, 胡晓光, 李晓筱, 杜卓群. 移动机器人全局路径规划算法综述[J]. 计算机科学, 2021, 48(10): 19 -29 .
[10] 晏旭, 马帅, 曾凤娇, 郭正华, 伍俊龙, 杨平, 许冰. 基于编码-解码器架构的光场深度估计方法[J]. 计算机科学, 2021, 48(10): 212 -219 .