"Your Eyes Tell You Have Used This Password Before": Identifying Password Reuse from Gaze and Keystroke Dynamics

TY - GEN

T1 - "Your Eyes Tell You Have Used This Password Before"

T2 - 2022 CHI Conference on Human Factors in Computing Systems, CHI 2022

AU - Abdrabou, Yasmeen

AU - Schütte, Johannes

AU - Shams, Ahmed

AU - Pfeuffer, Ken

AU - Buschek, Daniel

AU - Khamis, Mohamed

AU - Alt, Florian

PY - 2022

Y1 - 2022

N2 - 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 using 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.

AB - 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 using 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.

KW - Gaze Behavior

KW - Keystroke Dynamics

KW - Machine Learning

KW - Passwords

UR - https://www.scopus.com/pages/publications/85130573778

U2 - 10.1145/3491102.3517531

DO - 10.1145/3491102.3517531

M3 - Article in proceedings

AN - SCOPUS:85130573778

BT - CHI 2022 - Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

Y2 - 30 April 2022 through 5 May 2022

ER -