Recover Password  New User
Undergraduate Research Project Management System

Gaze-Based Password Authentication through Automatic Clustering of Gaze Points

Status Complete
Seeking Researchers No
Start Date 10/01/2011
End Date 10/15/2011
Funding Source Discovery Grant
Funding Amount
Community Partner
Related Course
Last Updated 09/21/2011 10:42PM
Keywords eye tracking, authentication


  Bogdan Hoanca, Kenrick Mock

Student Researchers
  Justin Weaver


Researchers have proposed systems in which users utilize an eye tracker to enter passwords by merely looking at the proper symbols on the computer monitor in the appropriate order. This authentication method is immune to the practice of shoulder-surfing: secretly observing the keystrokes of a legitimate user as they log in. In this paper we describe the EyeDent system in which users authenticate by looking at the symbols on an on-screen keyboard or keypad that correspond to their traditional password. Existing systems require the user to dwell or press a trigger when looking at each symbol. In EyeDent we explored if gaze points could be automatically clustered to determine the user's selected symbols instead of an explicit dwell or trigger. This approach has the benefit of allowing users to authenticate at their natural speed rather than with a fixed dwell time, doesn’t divulge the number of symbols in the password, and affords a more seamless authentication process. Results from our preliminary investigations indicate that quick and seamless authentication is possible using this scheme, but more work is needed to account for calibration error and to dynamically determine appropriate system parameters based on the characteristics of individual users.

Shared Project Files (e.g. papers, presentations)

File name Description Uploaded by