基于击键特征的身份认证系统设计与实现

Design and Implementation of Identity Authentication System Based on Keystroke Features

随着互联网技术的飞速发展,个人信息安全越来越被重视。基于用户名与口令的传统身份认证方式存在口令被泄密的风险,以人脸识别与指纹识别为主的生物特征识别技术因高昂的设备与复杂的算法使其通用性大受影响,采用生物行为特征对用户身份进行识别已成为研究热点。为此,设计一种口令与击键特征相结合的双因素认证方案,通过采集输入口令以及输入口令时的个人击键行为特征,结合新维信息优先思想,利用统计学算法与曼哈顿算法对采集到的用户击键行为特征数据进行分析与建模,并与当前用户的击键行为特征进行相似度匹配,从而对用户身份进行认证。基于该方案设计的系统不仅具有界面友好、操作方便、安全性高等特性,而且能自动显示每个用户的击键特征曲线,可作为重要信息系统的第一道安全闸门。

With the rapid development of Internet technology,personal information security has been paid more and more attention.The tradi⁃tional identity authentication method based on username and password carries the risk of password leakage.Biometric recognition technology,mainly based on facial recognition and fingerprint recognition,is greatly affected in its universality due to expensive equipment and complex al⁃gorithms.The use of biometric behavioral features to identify user identity has become a research hotspot.To this end,a dual factor authentica⁃tion scheme combining password and keystroke features is designed.By collecting input passwords and personal keystroke behavior characteris⁃tics during password input,combined with the new dimension information priority idea,statistical algorithms and Manhattan algorithm are used to analyze and model the collected user keystroke behavior feature data,and match it with the current user's keystroke behavior feature for similarity to authenticate the user's identity.The system designed based on this scheme not only has the characteristics of user-friendly in⁃terface,easy operation,and high security,but also can automatically display the keystroke characteristic curve of each user,which can serve as the first security gate of important information systems.