云计算网络中信息入侵特征识别仿真
|
摘要
对云计算网络中信息入侵特征的检测,可保障云计算系统的安全稳定性。对入侵信息特征的检测,需要得到入侵的频域特征包络幅度估计值,并对其进行降噪滤波处理,完成信息入侵特征识别。传统方法实时描述网络脆弱性的状态变迁过程,得到节点的状态和节点间的依赖关系,但忽略了对入侵进行降噪滤波处理,导致识别精度偏低。提出基于信息融合度传递的云计算网络中入侵信息特征识别方法。利用BSS方法对不同入侵信息进行特征识别,对不同入侵信息特征矢量进行分类,计算入侵信息的多普勒频移状态空间固有模态函数,得到其入侵的频域特征包络幅度估计值,对入侵信息进行降噪滤波处理,完成对云计算网络中入侵信息特征识别。仿真证明,所提方法识别精度较高,可以为保障云计算环境的安全稳定提供科学的依据。
A feature recognition method of intrusion information in cloud computing network is proposed based on transfer of information fusion degree.Firstly,the BSS method is used for feature recognition of different intrusion information,and the different feature vectors of intrusion information are classified.Then intrinsic mode function in state space of Doppler shift of intrusion information is calculated.Moreover,the estimate of envelope amplitude of frequency domain features of intrusion is obtained and noise reduction and filtration for intrusion information are carried out.Thus,feature recognition of intrusion information in cloud computing network is completed.Simulation proves that the proposed method has high recognition accuracy.It can provide a scientific basis for the security and stability of cloud computing environment.
A feature recognition method of intrusion information in cloud computing network is proposed based on transfer of information fusion degree.Firstly,the BSS method is used for feature recognition of different intrusion information,and the different feature vectors of intrusion information are classified.Then intrinsic mode function in state space of Doppler shift of intrusion information is calculated.Moreover,the estimate of envelope amplitude of frequency domain features of intrusion is obtained and noise reduction and filtration for intrusion information are carried out.Thus,feature recognition of intrusion information in cloud computing network is completed.Simulation proves that the proposed method has high recognition accuracy.It can provide a scientific basis for the security and stability of cloud computing environment.
引文
[1]欧群雍,杨杨.云计算恶意行为轨迹检测算法研究[J].计算机仿真,2016,33(2):335-339.
[2]黄兴利,等.基于云计算的Android恶意程序协同检测系统[J].计算机技术与发展,2016,26(8):79-82.
[3]张娜.基于云计算的恶意软件分析检测研究[J].软件导刊,2016,15(1):159-160.
[4]韩奕,等.基于云计算的恶意程序检测平台设计与实现[J].计算机工程,2014,40(4):26-31.
[5]景凡.云计算当道企业该如何阻止恶意软件[J].计算机与网络,2016,42(6):53-53.
[6]刘雅辉,等.大数据时代的个人隐私保护[J].计算机研究与发展,2015,52(1):229-247.
[7]卢笛,等.云计算下保障公平性的多资源分配算法[J].西安电子科技大学学报自然科学版,2014,41(3):162-168.
[8]王颖,等.云计算下信任反馈可信性评估模型研究[J].计算机工程与设计,2014,35(6):1906-1910.
[9]刘莹,等.云计算环境下基于行为预测的博弈信任模型[J].小型微型计算机系统,2015,36(10):2327-2333.
[10]蔡婷,陈昌志.云环境下基于UCON的访问控制模型研究[J].计算机科学,2014,41(s1):262-264.
[2]黄兴利,等.基于云计算的Android恶意程序协同检测系统[J].计算机技术与发展,2016,26(8):79-82.
[3]张娜.基于云计算的恶意软件分析检测研究[J].软件导刊,2016,15(1):159-160.
[4]韩奕,等.基于云计算的恶意程序检测平台设计与实现[J].计算机工程,2014,40(4):26-31.
[5]景凡.云计算当道企业该如何阻止恶意软件[J].计算机与网络,2016,42(6):53-53.
[6]刘雅辉,等.大数据时代的个人隐私保护[J].计算机研究与发展,2015,52(1):229-247.
[7]卢笛,等.云计算下保障公平性的多资源分配算法[J].西安电子科技大学学报自然科学版,2014,41(3):162-168.
[8]王颖,等.云计算下信任反馈可信性评估模型研究[J].计算机工程与设计,2014,35(6):1906-1910.
[9]刘莹,等.云计算环境下基于行为预测的博弈信任模型[J].小型微型计算机系统,2015,36(10):2327-2333.
[10]蔡婷,陈昌志.云环境下基于UCON的访问控制模型研究[J].计算机科学,2014,41(s1):262-264.