基于多元线性回归预测模型的sensor态势研究  

Research of Sensor Situation Based on Multiple Linear Regression Forecast Model

作　　者：张俭鸽[1] 李颖颖[1] 

机构地区：[1]信息工程大学电子技术学院,河南郑州450004

出　　处：《计算机技术与发展》2011年第9期229-232,共4页Computer Technology and Development

摘　　要：由于系统漏洞层出不穷,网络管理员也不容易获得用户主机的安全态势,如何在攻击者利用漏洞之前,对网络中用户主机的漏洞、脆弱性进行自动发现成为保障计算机网络安全、平稳运行的关键问题。文中针对多元线性回归预测模型算法,首先利用最小二乘法实现对多元线性回归方程的求解,然后利用"t-检验"检验回归系数的显著性,实现对sensor安全的精确预测,使网络管理员能直观了解到sensor的全状况,以寻求最低的事故率、最少的损失和最优的安全投资效益。Due to system vulnerability emerging in endlessly,and administrators of network acquiring security situation of customer host not easily also,how to automatically discover the vulnerability and frangibility of customer host on the internet before attackers utilize the vulnerability becomes a sixty-four-dollar question of ensuring the network run surely and placidly.In allusion to the algorithms of multiple linear regression forecast model,realize the forecast of sensor security exactly utiliz the least square to solve the equation of multiple linear regression firstly,and then utilize t-test to test the significance of regression coefficient.Thus administrators of network are able to know the whole status of sensor intuitively,and seek the lowest accident rate,the least loss,and the best security investment re-sults.

关 键 词：漏洞 安全态势 多元线性回归预测模型 最小二乘法 t-检验 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]