基于键盘行为进行用户识别的方法与应用  

Method of User Identification Based on Keystroke Behavior and its Application

作　　者：王昱杰 赵培海 王咪咪[1] 

机构地区：[1]同济大学电子与信息工程学院,上海201800

出　　处：《计算机科学》2015年第11期203-207,234,共6页Computer Science

基　　金：港澳台科技合作专项(2013DFM10100)资助

摘　　要：基于键盘行为的已有研究大多限制在实验环境下,并限定用户的输入为特定字符串,或只在有限实验参与者中进行识别,从而导致其无法应用在真实的环境中。为了克服已有研究的局限,解决真实环境中正负样本不均衡和负样本缺失的问题,对真实环境下一千万条用户击键行为进行分析,提出了一种基于键盘行为进行用户识别的方法。该方法使用击键持续时间和击键间隔时间描述用户的击键行为,通过实验选择马氏距离进行用户击键行为相似度的对比,并对未知击键行为进行预测。实验结果表明,该方法可获得80%的预测准确率。Most researches on keyboard behavior have been limited in experimental environment, which force user to in- put a specific string or limite the number of participants, so the result of research can＇t apply into real production envi- ronment. To overcome this limitation and resolve the problem of the unbalanced samples between positive and negative and the problem of lacking negative samples, ten million keystroke behaviors were analyzed, and a method for user iden- tification was introduced. The duration and the interval of keystroke describing the user＇s behavior are used, and the similarity of different keystrokes is measured by Mahalanobis distance. The result of experiment shows that our method gets an accuracy of 80%.

关 键 词：用户识别 身份校验 击键行为 马氏距离 向量相似性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]