Keystroke Biometrics Application for On-Line Testing
Mary Curtin, Division of Computer Science, Mathematics and Science, College of Professional Studies
Abstract
In today’s world, there is an ever-growing need to authenticate and identify individuals automatically. The current technologies of using a PIN or password for these purposes are inadequate because they may be disclosed, transferred and may be hard to remember. Biometric-based authentication and identification methods are emerging as the most reliable.
A biometric is a measurable, physical characteristic or personal behavioral trait used to recognize the identity, or verify the claimed identity, of an individual. It is also an information pattern used to identify a particular body, such as a fingerprint, autograph, retina scan, password, etc. Previous works in the area of biometrics have shown that keystroke dynamics is a real possibility to authenticate a user. This dissertation is will demonstrate the role of keystroke biometrics as an important method to be used, by computers, to measure user characteristics to achieve a secure identification or verification.
I will investigate using the application of keystroke software system for on-line test takers and determine the results using the nearest neighbor algorithm. Experimental results will show that the nearest neighbor pattern can greatly improve the performance of keystroke matching in both accuracy and efficiency, and it is very suitable for applications in password hardening.