|
|
|
| Verification Based on Keystroke Biologic Characteristics Using Support Vector Data Description |
| NI Gui-Qiang, LI Jia-Zhen, PAN Zhi-Song, MIAO Zhi-Min |
| Institute of Command Automation, PLA University of Science and Technology, Nanjing 210007 |
|
|
|
|
Abstract Since computer users are different at degrees of familiarity with keyboards and keystroke habits, each user has his particular keystroke characteristics. To one user, his keystroke characteristics are normal classes, and all the other users' are abnormal. Thus this problem can be resolved by one-class classifier. The keystroke verification based on support vector data description (SVDD) is proposed. Through experiments, SVDD is compared with BP, RBF and SOM, and the results show SVDD has better performance. It decreases impostor pass rate (IPR) from 28.9% to 0.28%. Finally, an password & keystroke characteristics identity verification system is presented.
|
|
Received: 18 October 2007
|
|
|
|
|
|
[1] Miller B. Vital Signs of Identity. IEEE Spectrum, 1994, 31(2): 22-30
[2] Zhu Ming, Zhou Jin, Wang Jikang. A New Approach for User Authentication Based on Biometrics. Computer Engineering, 2002, 28(10): 138-139,142 (in Chinese)
(朱 明,周 津,王继康.基于击键特征的用户身份认证新方法.计算机工程, 2002, 28(10): 138-139,142)
[3] Liu Xuejun, Chen Songcan, Peng Hongjing. Computer Keystroker Verification Based on Support Vector Machines. Journal of Computer Research and Development, 2002, 39(9): 1082-1086 (in Chinese)
(刘学军,陈松灿,彭宏京.基于支持向量机的计算机键盘用户身份验真.计算机研究与发展, 2002, 39(9): 1082-1086)
[4] Rui Ting, Shen Chunlin, Qi Tian, et al. Identity Verification Based on Keystroke Feature Using HMM. Computer Engineering, 2005, 31(2): 7-9,23 (in Chinese)
(芮 挺,沈春林,Qi Tian,等.基于HMM的击键特征用户身份认证.计算机工程, 2005, 31(2): 7-9,23)
[5] Peacock A. Learning User Keystroke Latency Patterns [EB/OL]. [2000-04-01]. http://pel.cs.byu.edu/~alen/personal/CourseWork/CS572/keystrolePaper, 2000
[6] Kancholia V, Pandit S. Biometric Authentication Using Random Distributions // Proc of the 15th Canadian Information Technology Security Symposium. Ottawa, Canada, 2003: 1-8
[7] Schlkopf B, Platt J C, Shawe-Taylor J, et al. Estimating the Support of a High-Dimensional Distribution. Neural Computation, 2001, 13(7): 1443-1471
[8] Campbell C, Bennett K P. A Linear Programming Approach to Novelty Detection. Advances in Neural Information Processing System, 2001, 14(4): 203-208
[9] Tax D M J. One-Class Classification. Ph.D Dissertation. Delft, Netherlands: Delft University of Technology. Information and Communication Theory Group, 2001
[10] Tax D M J, Duin R P W. Support Vector Data Description. Machine Learning, 2004, 54(1): 45-66
[11] Manevitz L M, Yousef M. One-Class SVMs for Document Classification. Journal of Machine Learning Research, 2001, 2(2): 139-154
[12] Obaidat M S, Sadoun B. Verification of Computer Users Using Keystroke Dynamic. IEEE Trans on Systems, Man and Cybernetics, 1997, 27(2): 261-269
[13] Liu Zhibo. Research of One-Class Classification and Its Application in Keystroker Verification System. Nanjing, China: Nanjing University of Aeronautics and Astronautics. College of Information Science and Technology, 2004 (in Chinese)
(刘志波.单类分类器研究及其在击键认证系统中的应用实现.硕士学位论文.南京:南京航空航天大学.信息科学与技术学院, 2004) |
|
|
|
2008, Vol. 21 
