期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2011
卷号：2
期号：6
页码：2765-2772
出版社：TechScience Publications
摘要：Web based authentication provide remote authentication and security control mechanism. Password typing is the most widely used identity verification method in World Wide Web based Electronic Commerce (EC). Due to its simplicity, it is vulnerable to imposter attacks. Keystroke dynamics and password checking can be combined to result in a more secure verification system. We proposed an association of ideas of neural network that is trained with the timing vectors of the owner's keystroke dynamics and then used to discriminate between the owner and an imposter. This paper presents a novel application of neural nets to user identity authentication on computer-access security system. A three-layered back propagation neural network with a flexible number of input nodes was used to discriminate valid users and impostors according to each individual's password keystroke pattern. Keystroke latency is measured for each user and forms the patterns of keyboard dynamics. System verification performance was improved by setting convergence criteria RMSE (Root Mean Square Error) to a smaller threshold value during training procedure. The resulting system gave 1.1% FAR (False Alarm Rate) in rejecting valid users and zero IPR (Impostor Pass Rate) in accepting no impostors. An imposter typing the correct password can be detected with very high accuracy using the proposed approach. This approach can be effectively implemented by a Java applet and used in the World Wide Web. A suitable network structure for this application was also discussed. Furthermore, the implementation of this approach requires no special hardware and is easy to be integrated with most computer systems.
