Presenter(s)
Bradley Budach
Abstract
This study explores the use of keystroke dynamics as a behavioral biometric for user identification. Unlike physiological biometrics, such as fingerprints or facial recognition, keystroke dynamics leverages the unique typing patterns of individuals to create a distinctive signature. This research was to develop a machine learning-based system that utilizes keystroke dynamics for continuous and unobtrusive user authentication. By collecting and analyzing keystroke data from multiple users, relevant features were extracted and used to train a machine learning model to identify user keystroke signatures with an equal error rate of 0.11. This model allows for reliable and scalable authentication that can provide an additional layer of security on top of traditional security measures. This study was done as part of my Computer Science Research Seminar course
College
College of Science & Engineering
Department
Computer Science
Campus
Winona
First Advisor/Mentor
Mingrui Zhang
Second Advisor/Mentor
Sudharsan Iyengar
Third Advisor/Mentor
Trung Nguyen
Start Date
4-24-2025 10:00 AM
End Date
4-24-2025 11:00 AM
Presentation Type
Poster Session
Format of Presentation or Performance
In-Person
Session
1b=10am-11am
Poster Number
10
Included in
Using Keystroke Dynamics Behavioral Biometrics to Identify Users
This study explores the use of keystroke dynamics as a behavioral biometric for user identification. Unlike physiological biometrics, such as fingerprints or facial recognition, keystroke dynamics leverages the unique typing patterns of individuals to create a distinctive signature. This research was to develop a machine learning-based system that utilizes keystroke dynamics for continuous and unobtrusive user authentication. By collecting and analyzing keystroke data from multiple users, relevant features were extracted and used to train a machine learning model to identify user keystroke signatures with an equal error rate of 0.11. This model allows for reliable and scalable authentication that can provide an additional layer of security on top of traditional security measures. This study was done as part of my Computer Science Research Seminar course
Comments
No poster file