"Your Eyes Say You Have Used This Password Before"
Subtitle:
Identifying Password Reuse from Gaze Behavior and Keystroke Dynamics
Title of conference publication:
CHI '22: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems
Conference title:
Conference on Human Factors in Computing Systems (2022, New Orleans, LA)
Venue:
New Orleans, LA
Year of conference:
2022
Date of conference beginning:
30.04.2022
Date of conference ending:
05.05.2022
Place of publication:
New York, NY
Publisher:
Association for Computing Machinery
Year:
2022
Pages from - to:
400
Language:
Englisch
Abstract:
A significant drawback of text passwords for end-user authentication is password reuse. We propose a novel approach to detect password reuse by leveraging gaze as well as typing behavior and study its accuracy. We collected gaze and typing behavior from 49 users while creating accounts for 1) a webmail client and 2) a news website. While most participants came up with a new password, 32% reported having reused an old password when setting up their accounts. We then compared different ML models to detect password reuse from the collected data. Our models achieve an accuracy of up to 87.7% in detecting password reuse from gaze, 75.8% accuracy from typing, and 88.75% when considering both types of behavior. We demonstrate that e̊visedusing gaze, password reuse can already be detected during the registration process, before users entered their password. Our work paves the road for developing novel interventions to prevent password reuse. «
A significant drawback of text passwords for end-user authentication is password reuse. We propose a novel approach to detect password reuse by leveraging gaze as well as typing behavior and study its accuracy. We collected gaze and typing behavior from 49 users while creating accounts for 1) a webmail client and 2) a news website. While most participants came up with a new password, 32% reported having reused an old password when setting up their accounts. We then compared different ML models t... »