Using mouse strokes to verify user identity

• Main Author: Toh, Jing Sheng.
• Other Authors: School of Computer Engineering
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering::Computer applications::Social and behavioral sciences
• Online Access: http://hdl.handle.net/10356/51958
• Institution: Nanyang Technological University

As the technology advances, many interesting approaches have emerged to tackle the flaw of the traditional authentication techniques which verify users based on something that one knows or possesses. Not only do these systems expose their users to identity theft, users could also forget their password or misplace the hardware token used for authentication. Many new approaches involve the use of biometric authentication which is based on inherent and unique characteristics of the user. Such authentication could be based on physiological biometrics such as fingerprint verification. However, the drawback is that they require dedicated hardware, which is expensive and not readily available. This project aims to develop an Internet browser based authentication system that would allow verification of user simply by using mouse strokes. Using mouse strokes is a form of behavioral biometrics that do not require special designated devices since a mouse is a cheap and widely available piece of peripheral hardware that is commonly found alongside computer systems. The project consists of a client and server model. The main responsibility of the client is to capture mouse strokes data and sending them to the server for verification. The server consists of a checking algorithm, which would be able to determine if two sets of mouse strokes data is from a single user. Web pages for registration, login, and reset mouse strokes along with server based logic verification pages and database completes the functionalities of the project. At the end of the project, an Internet browser based authentication system using mouse strokes was completed with encouraging results in reliability, robustness and security. There are still work that can be done in the future by conducting more experiments to further refine the features and checking algorithm used in this project. Expansion of the project to another platform can also be considered.