Rough Outlier Detection Based Security Risk Analysis Methodology  

作　　者：Li Qianmu Li Jia 

机构地区：[1]Department of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing210094,P.R.China [2]Wu Xi Research Institute,Nanjing University of Science and Technology,Wuxi 214192,P.R.China

出　　处：《China Communications》2012年第7期14-21,共8页中国通信（英文版）

基　　金：the Jiangsu 973 Scientific Project，the National Natural Science Foundation of China，the Jiangsu Natural Science Foundation，the Aerospace Innovation Fund，the Lianyungang Science & Technology Project

摘　　要：Security is a nonfunctional information system attribute that plays a crucial role in wide sensor network application domains. Security risk can be quantified as the combination of the probability that a sensor network system may fail and the evaluation of the severity of the damage caused by the failure. In this paper, we devise a methodology of Rough Outlier Detection (ROD) for the detection of security-based risk factor, which originates from violations of attack requirements (namely, attack risks). The methodology elaborates dimension reduction method to analyze the attack risk probability from high dimensional and nonlinear data set, and combines it with rough redundancy reduction and the distance measurement of kernel function which is obtained using the ROD. In this way, it is possible to determine the risky scenarios, and the analysis feedback can be used to improve the sensor network system design. We illustrate the methodology in the DARPA case set study using step-by-step approach and then prove that the method is effective in lowering the rate of false alarm.Security is a nonfunctional information system attribute that plays a crucial role in wide sensor network application domains. Security risk can be quantified as the combination of the probability that a sensor network system may fail and the evaluation of the severity of the damage caused by the failure. In this paper, we devise a methodology of Rough Outlier Detection （ROD） for the detection of security-based risk factor, which originates from violations of attack requirements （namely, attack risks）. The methodology elaborates dimension reduction method to analyze the attack risk probability from high dimensional and nonlinear data set, and combines it with rough redundancy reduction and the distance measure- ment of kernel function which is obtained using the ROD. In this way, it is possible to determine the risky scenarios, and the analysis feedback can be used to improve the sensor network system design. We illustrate the methodology in the DARPA case set study using step-by-step approach and then prove that the method is effective in lowering the rate of false alarm.

关 键 词：rough outlier risk analysis dimensionality reduction 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置] TS201.6[自动化与计算机技术—控制科学与工程]