一种面向击键动态身份认证的多模板选择算法

J4 ›› 2014, Vol. 36 ›› Issue (01): 73-82.

一种面向击键动态身份认证的多模板选择算法

李福祥1,霍建秋2,林慕清1,唐晶1,周福才2

(1.东北大学信息科学与工程学院, 辽宁沈阳 110819；2.东北大学软件学院,辽宁沈阳 110819)

收稿日期:2013-08-03 修回日期:2013-10-25 出版日期:2014-01-25 发布日期:2014-01-25
基金资助:
国家科技重大专项项目（2013ZX03002006）；辽宁省百千万人才工程项目（2011921071）；国家863计划资助项目（2009AA01Z122）

A new multitemplate selection algorithm for
keystroke dynamic identity authentication

LI Fuxiang1,HUO Jianqiu2,LIN Muqing1,TANG Jing1,ZHOU Fucai2

(1.College of Information Science and Engineering,Northeastern University,Shenyang 110819;
2.College of Software,Northeastern University,Shenyang 110819,China)

Received:2013-08-03 Revised:2013-10-25 Online:2014-01-25 Published:2014-01-25

摘要/Abstract

摘要：

在击键动态身份认证系统中，样本采集和模板建立直接影响系统性能。目前单模板击键认证系统存在无法使错误接受率和错误拒绝率都降低到可接受范围内的不足。为此将多模板思想引入击键认证过程中，在提出最大认证概率算法和最小认证概率算法后，提出均衡概率多模板选择算法，将两种错误率都控制在合理范围内。通过实验同GMMS算法进行对比，并研究了模板数和模板样本数对认证结果的影响，最后与单模板认证系统进行了比较分析。

关键词: 生物认证, 击键动态身份认证, 多模板选择

Abstract:

Sample collection and the establishment of the template are crucial for keystroke dynamic identity authentication systems. So far, the single template systems cannot decrease the false reject/accept rate(FRR/FAR) into the reasonable range. The multitemplate method is introduced into the keystroke authentication, and then a new multitemplate selection algorithm is proposed to balance the FRR and FAR after the most/least authentication probability algorithm is presented. Experiments are done to compare the proposed algorithm with the GMMS, and the factors that can influence the authentication results are analyzed. At last, the advantage of multitemplate system is also shown, compared with the singletemplate authentication systems.

Key words: biometric authentication;keystroke dynamic identity authentication;multitemplate selection

李福祥1,霍建秋2,林慕清1,唐晶1,周福才2. 一种面向击键动态身份认证的多模板选择算法[J]. J4, 2014, 36(01): 73-82.

LI Fuxiang1,HUO Jianqiu2,LIN Muqing1,TANG Jing1,ZHOU Fucai2. A new multitemplate selection algorithm for
keystroke dynamic identity authentication [J]. J4, 2014, 36(01): 73-82.

参考文献［23］

［1］	Spillane R. Keyboard apparatus for personal identification［J］. IBM Technical Disclosure Bulletin, 1975, 17（3346）:1.
［2］	Gunetti D,Picardi C.Keystroke analysis of free text［J］. ACM Transactions on Information and System Security, 2005, 8(3):312347.
［3］	Bleha S,Slivinsky C,Hussien B.Computer access security systems using keystroke dynamics［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(12):12171222.
［4］	Bleha S A, Obaidat M S. Computer users verification using the perceptron algorithm［J］. IEEE Transactions on System, Man and Cybernetics, 1993, 23(3):900903.
［5］	Brown M,Rogers S J.User identification via keystroke characteristics of typed names using neural networks［J］. International Journal of ManMachine Studies, 1993, 39(6):9991014.
［6］	Obaidat M S, Sadoun B. A simulation evaluation study of neural network techniques to computer user identification［J］. Information Sciences:An International Journal, 1997, 102(14):239258.
［7］	Chen W, Chang W. Applying hidden markov models to keystroke pattern analysis for password verification［C］∥Proc of IEEE International Conference on Information Reuse and Integration, 2004:467474.
［8］	Rui Ting, Shen Chunlin, Zhang Jinlin. HMMbased user authentication with keystroke features［J］. Computer Engineering, 2005, 31(2):79.(in Chinese)
［9］	Jiang C H, Shieh S, Liu J C. Keystroke statistical learning model for web authentication［C］∥Proc of ACM Symposium on Information, Computer and Communications Security, 2007:359361.
［10］	Liu Renqing. Predict user behavior in order to assist the integration of identity recognized statistical methods［D］. Taiwan:Chiao Tung University, 2007.(in Chinese)
［11］	Stefan D,Yao D.Keystrokedynamics authentication against synthetic forgeries［C］∥Proc of the 6th International Conference on Collaborative Computing:Networking, Applications and Worksharing, 2010:18.
［12］	Buchoux A, Clarke N L. Deployment of keystroke analysis on a smartphone［C］∥Proc of Australian Information Security Management Conference, 2008:48.
［13］	Ogihara A, Matsumuar H, Shiozaki A. Biometric verification using keystroke motion and key press timing for ATM user authentication［C］∥Proc of Intelligent Signal Processing and Communications, 2006:223226.
［14］	Clarke N L, Furnell S M, Lines B M, et al. Keystroke dynamics on a mobile handset:A feasibility study［J］. Information Management & Computer Security, 2003, 11(4):161166.
［15］	Jain A, Uludag U, Ross A. Biometric template selection:A case study in fingerprints［C］∥Proc of the 4the International Conference on Audio and VideoBased Person Authentication, 2003:335342.
［16］	Li Y, Yin J, Zhu E, et al. Studies of fingerprint template selection and update［C］∥Proc of FGCN 2008 Workshops and Symposia, 2009:150163.
［17］	Maiorana E, Campisi P, GonzálezCarballo N, et al. Keystroke dynamics authentication for mobile phones［C］∥Proc of 2011 ACM Symposium on Applied Computing, 2011:2126.
［18］	Pawate B I, Robinson P D. Implementation of an HMMbased, speakerindependent speech recognition system on the TMS320C2x and TMS320C5x［M］. Dallas:Texas Instruments Incorporated, 1996.
［19］	Xie Jinhui. Hidden Markov model and its application in speech processing applications［M］. Wuhan:Huazhong University of Technology Press, 1995.(in Chinese)
［20］	Jarmo I. Keystroke dynamics ［EB/OL］. ［20121025］. http://www.it.lut.fi/kurssit/0304/010970000/seminars/Ilonen.pdf.
［21］	Mansfield A J, Wayman J L. Best practices in testing and reporting performance of biometric devices ［R］. NPL Report CMSC, UK:Centre for Mathematics and Scientific Computing, National Physical Laboratory, 2002.
［22］	Maltoni D, Maio D, Jain A K, et al. Handbook of fingerprint recognition［M］. NY:Springer, 2009.
［23］	Li Xiuyan. Research on personal identity recognition method based on multibiometric［D］. Tianjin:Tianjin University, 2010.(in Chinese)
	附中文参考文献:
［8］	芮挺, 沈春林, 张金林. 基于HMM的击键特征用户身份认证［J］. 计算机工程, 2005, 31(2):79.
［10］	刘仁清. 预测使用者行为以辅助身份辨识的融合统计方法［D］. 台湾:交通大学, 2007.
［19］	谢锦辉. 隐马尔可夫模型及其在语音处理中的应用［M］. 武汉:华中理工大学出版社, 1995.
［23］	李秀艳. 多生物特征身份识别方法研究［D］. 天津:天津大学, 2010.