Design Biometric System to Verify
Online Test Takers on Mouse/Keystroke Input

Background

By analyzing mouse trajectories and mouse clicks it is possible to authenticate the identity of the user with reasonable accuracy, although most studies found mouse movement to be a weaker (less accurate) biometric than keystroke dynamics.

Similar to keystroke biometric studies, two primary types of mouse movement studies have been conducted - those on a fixed sequence of mouse moves and those on arbitrary mouse input, and the arbitrary input can be structured to various degrees [3, 4].

There are several applications that can utilize mouse movement biometric information, such as intrusion detection and enhancing/augmenting keystroke and other biometrics. For many biometrics the research interest is to determine the level of accuracy possible in various experimental situations as a function of the quantity of input data and the number of users. Recent project work focused on verifying the user's identity on various types of structured, application-specific mouse movement input [1, 2].

Project

The study undertaken here will focus on authenticating online test takers using mouse and keystroke input. The mouse data will be captured from student input on multiple choice (and similar) questions, and the keystroke data will be captured from student input on short answer (and similar) questions. Our keystroke data capture and system is well understood, so we will focus primarily on designing the mouse input structure this semester.

How online tests might appear to the students is now presented. At the beginning of the semester the online students would provide information in a format similar to the tests, and a brief example is shown here.

Students, please answer the following questions to provide general information for your instructor. These questions are in the format of the tests you will take later this semester and your behavioral biometrics will be captured here to establish a user profile to verify your identity on the upcoming tests (this sentence could be omitted if the behavioral biometric verification is to be kept secret). Example multiple-choice questions:

  1. My current status is: a) Freshman b) Sophomore c) Junior d) Senior e) Graduate student
  2. Other than voice conversations, I use my smart phone primarily for: a) texting b) email c) social networking d) I don't have a smart phone
  3. etc.
Example short-answer questions:
  1. Why are you taking this course?
  2. What do you hope to learn from the course?
  3. etc.
There might normally be 10 or more multiple-choice questions and five or more short-answer questions. For each multiple-choice question, the student is required to move the mouse cursor to the appropriate response button (usually one of four choices) and click on it. For each short-answer question, the student is required to enter (type) several sentences of text. The data recorded by the student is continually cross-referenced throughout the semester to ensure a change in identity has not occurred. Additionally, the database may be used to authenticate students across multiple courses.

References (first five are the most important)

  1. Hedieh Zandikarimi, Frank Lin, Celia Carlos, Justin Correa, Phil Dressner, and Vinnie Monaco, Design of a Mouse Movement Biometric System to Verify the Identity of Students Taking Multiple-Choice Online Tests, Proc. Research Day, CSIS, Pace University, May 2014.
  2. Francisco Betances, Adam Pine, Gerald Thompson, Hedieh Zandikarimi, and Vinnie Monaco, Mouse Biometric Authentication, Proc. Research Day, CSIS, Pace University, May 2014.
  3. Pedro Xavier de Oliveira, Venugopala Channarayappa, Eamonn O'Donnel, Bappaditya Sinha, Aswinkumar Vadakkencherry, Tushar Londhe, Umesh Gatkal, Ned Bakelman, John V. Monaco, and Charles C. Tappert, Mouse Movement Biometric System, Proc. Research Day, CSIS, Pace University, 2013. slides
  4. Chao Shen, et al., User Authentication Through Mouse Dynamics, IEEE Trans. Info. Forensics and Security, 8-1, Jan 2013.
  5. Allen Newell, Section on Fitts' Law, Unified Theories of Cognition (The William James Lectures), Harvard University Press, 1994.
  6. Nkem Ajufor, Antony Amalraj, Rafael Diaz, Mohammed Islam, Michael Lampe, Refinement of a Mouse Movement Biometric System, Proc. Research Day, CSIS, Pace University, 2007.
  7. Nan Zheng, Aaron Paloski, and Haining Wang, An Efficient User Verification System via Mouse Movements, CCS’11, Chicago, October 2011.
  8. Maja Pusara and Carla E. Brodley, User Re-Authentication via Mouse Movements, VizSEC/DMSEC'04, Washington DC, 2004.