基于Levenberg-Marquardt算法的用户鉴别  

The Authentication of the Computer Users Based on Levenberg-Marquardt Algorithm

作　　者：王琛[1] 

机构地区：[1]北京航空航天大学,北京100083

出　　处：《山西师范大学学报（自然科学版）》2005年第2期17-20,共4页Journal of Shanxi Normal University(Natural Science Edition)

摘　　要：为了维护计算机系统的安全,一般通过设置用户口令以便进行身份鉴别,防止他人冒名顶替.口令鉴别的主要弱点在于,一旦被窃,冒名顶替者就可以轻而易举地进入用户的私人账户进行非法活动.击键动力学的研究是给口令加上一个简便而有效的保护措施.击键动力学方法通过获取并分析用户敲击键盘的特征数据,自动地识别出用户的真实身份.这一辅助身份鉴别的关键问题主要是寻找准确率高、执行速度快的识别算法.本论文采用Levenberg-Marquardt(LM)算法对上述存在的问题进行了研究.In order to protect computer system, password is the most widely used method to control the access of computer system by authenticating the users′ identity. However, the policy of password is vulnerable to impostor attacks due to its simplicity. Therefore, the original intention of keystroke dynamics is to provide a convenient and effective protection on password verification. In keystroke dynamics, the characteristics of a user′ keystrokes is captured when password is being typed, and is analyzed by algorithms to automatically recognize the authentic identity. What is critical for such an auxiliary identity authentication is to find a recognition algorithm with high accuracy and high speed. In this thesis, these problems are explored in depth, and Levenberg-Marquardt algorithm is adopted for data analysis.

关 键 词：LEVENBERG-MARQUARDT算法 用户鉴别 身份鉴别 计算机系统 动力学方法 用户口令 口令鉴别 保护措施 特征数据 关键问题 识别算法 执行速度 准确率 顶替 键盘 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP309[自动化与计算机技术—控制科学与工程]