云组合服务网络的异常植入数据检测算法
|
摘要
云组合服务网络在路由转发控制受到节点的同态扰动影响,容易受到植入入侵,为了提高网络的安全性,提出一种基于阈值组合判决的云组合服务网络的异常植入数据检测算法。构建网络异常植入数据的统计特征模型,采用大数据挖掘技术进行云组合服务网络异常植入数据特征检测和滤波分析,提取云组合服务网络数据的谱特征量,采用支持向量机学习方法进行云组合服务网络的异常植入数据检测过程中的自适应寻优控制,采用双门限阈值组合判决方法,实现对目标数据的准确检测,提高对异常植入数据的准确定位检测能力。仿真结果表明,采用该方法进行云组合服务网络异常植入数据检测的准确概率较高,检测性能较好,提高了网络安全性。
In order to improve the security of cloud composition service network,a detection algorithm of abnormal embedding data based on threshold combination decision is proposed for cloud composition service network,which is easily invaded by the homomorphic disturbance of nodes in routing and forwarding control. The statistical feature model of network abnormal placement data is constructed. Big data mining technology is used to detect and filter the feature of cloud composition service networkanomaly embedding data,and the spectral feature quantity of cloud composition service network data is extracted. The support vector machine learning method is used to control the adaptive optimization in the detection process of anomaly embedding data in cloud composition service network,and the double threshold combination decision method is adopted to realize the accurate detection of the target data and improve the ability of accurate localization and detection of anomaly embedding data. The simulation results show that the accuracy probability of the proposed method is higher,the detection performance is better,and the network security is improved.
In order to improve the security of cloud composition service network,a detection algorithm of abnormal embedding data based on threshold combination decision is proposed for cloud composition service network,which is easily invaded by the homomorphic disturbance of nodes in routing and forwarding control. The statistical feature model of network abnormal placement data is constructed. Big data mining technology is used to detect and filter the feature of cloud composition service networkanomaly embedding data,and the spectral feature quantity of cloud composition service network data is extracted. The support vector machine learning method is used to control the adaptive optimization in the detection process of anomaly embedding data in cloud composition service network,and the double threshold combination decision method is adopted to realize the accurate detection of the target data and improve the ability of accurate localization and detection of anomaly embedding data. The simulation results show that the accuracy probability of the proposed method is higher,the detection performance is better,and the network security is improved.
引文
[1]陆兴华,陈平华.基于定量递归联合熵特征重构的缓冲区流量预测算法[J].计算机科学,2015,42(4):68-71.
[2]沈渊.基于入侵关联跟踪的P2P网络入侵检测方法[J].科技通报,2013,29(6):32-34.
[3]Moradi M,Keyvanpour M R. An analytical review of XML association rules mining[J]. Artificial Intelligence Review,2015,43(2):277-300.
[4]Dong G L,Ryu K S,Bashir M,et al. Discovering medical knowledge using association rule mining in young adults with acute myocardial infarction[J]. Journal of Medical Systems,2013,37(2):1-10.
[5]Khalili A,Sami A. SysDetect:a systematic approach to critical state determination for industrial intrusion detection systems using Apriori algorithm[J]. Journal of Process Control,2015,2776:154-160.
[6]Mernik M,Liu S H,Karaboga M D,et al. On clarifying misconceptions when comparing variants of the Artificial Bee Colony Algorithm by offering a new implementation[J]. Infor mation Sciences,2015,291(10):115-127.
[7]章武媚,陈庆章.引入偏移量递阶控制的网络入侵HHT检测算法[J].计算机科学,2014,41(12):107-111.
[8]杨雷,李贵鹏,张萍.改进的Wolf一步预测的网络异常流量检测[J].科技通报,2014,30(2):47-49.
[9]黎峰,吴春明.基于能量管理的网络入侵防波动控制方法研究[J].计算机仿真,2013,30(12):45-48,335.
[10]黄潮.云计算环境下的海量光纤通信故障数据挖掘算法研究[J].激光杂志,2017,38(1):96-100.
[11]黄辉,陆冬梅,胡涛. NSD序列的Chover型重对数律[J].吉林大学学报:理学版,2018,56(5):1113-1118.
[12]都琳,张莹,胡高歌,等.一种双寡头垄断Cournot-Puu模型的混沌控制研究[J].应用数学和力学,2017,38(2):224-232.
[2]沈渊.基于入侵关联跟踪的P2P网络入侵检测方法[J].科技通报,2013,29(6):32-34.
[3]Moradi M,Keyvanpour M R. An analytical review of XML association rules mining[J]. Artificial Intelligence Review,2015,43(2):277-300.
[4]Dong G L,Ryu K S,Bashir M,et al. Discovering medical knowledge using association rule mining in young adults with acute myocardial infarction[J]. Journal of Medical Systems,2013,37(2):1-10.
[5]Khalili A,Sami A. SysDetect:a systematic approach to critical state determination for industrial intrusion detection systems using Apriori algorithm[J]. Journal of Process Control,2015,2776:154-160.
[6]Mernik M,Liu S H,Karaboga M D,et al. On clarifying misconceptions when comparing variants of the Artificial Bee Colony Algorithm by offering a new implementation[J]. Infor mation Sciences,2015,291(10):115-127.
[7]章武媚,陈庆章.引入偏移量递阶控制的网络入侵HHT检测算法[J].计算机科学,2014,41(12):107-111.
[8]杨雷,李贵鹏,张萍.改进的Wolf一步预测的网络异常流量检测[J].科技通报,2014,30(2):47-49.
[9]黎峰,吴春明.基于能量管理的网络入侵防波动控制方法研究[J].计算机仿真,2013,30(12):45-48,335.
[10]黄潮.云计算环境下的海量光纤通信故障数据挖掘算法研究[J].激光杂志,2017,38(1):96-100.
[11]黄辉,陆冬梅,胡涛. NSD序列的Chover型重对数律[J].吉林大学学报:理学版,2018,56(5):1113-1118.
[12]都琳,张莹,胡高歌,等.一种双寡头垄断Cournot-Puu模型的混沌控制研究[J].应用数学和力学,2017,38(2):224-232.