Mouse Movement System

Background

Although our initial aim in this work was the authentication of a remote user, we started with the identification problem to show feasibility. As online classes gain a larger share of the educational market, it becomes necessary to verify that the person taking a test is actually the student enrolled in the class. Research has already shown that keystroke biometrics can aid in identification of an individual. Unfortunately, most online tests are multiple choice or true/false. These tests typically require little typing, because the user is selecting answers by moving to and clicking on a screen location. By tracking the movement of the mouse through different arcs it should be possible to verify or identify individuals, at least to some extent. The comparison would be made against an existing profile, just as has been successfully done with keystrokes. Additionally, mouse movement biometrics could be used to enhance or augment keystroke biometrics. Two related technical papers are: Identification Using Mouse Forces and User Re-Authentication via Mouse Movements (the second appears more relevant).

Project

We will continue to develop and test the system previously developed and subsequently tested.

This semester's project will have two primary focuses. First, we will become familiar with the system and collect as much additional data as possible, including data from each team member.

Second, and most importantly, we will format the feature-vector data for ease of processing by other project systems, specifically the Biometric Authentication System and the Data Mining Systems teams.

Also, if time permits, we will rerun some of the previous experiments, possibly improve the method of running experiments, and run larger experiments, combining the new data with the old.