Reliable keystroke biometric system based on a small number of keystroke samples

Authors:
Woojin Chang
Affiliations:
Department of Industrial Engineering, Seoul National University, Seoul, Korea
Venue:
ETRICS'06 Proceedings of the 2006 international conference on Emerging Trends in Information and Communication Security
Year:
2006

Citing 3
Cited 2

Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Typing Patterns: A Key to User Identification

IEEE Security and Privacy
Keystroke biometric system using wavelets

ICB'06 Proceedings of the 2006 international conference on Advances in Biometrics

Fuzzy and Markov models for keystroke biometrics authentication

SMO'07 Proceedings of the 7th WSEAS International Conference on Simulation, Modelling and Optimization
Review Article: Biometric personal authentication using keystroke dynamics: A review

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Less than ten keystroke samples from a legitimate user can make Keystroke Biometric System (KBS) reliable. Based on user's original keystroke samples, artificial keystroke samples are produced by resampling techniques in both time and wavelets domains. KBS constructed from these original and artificial keystroke samples shows smaller error rates than KBS from original keystroke samples only. Our resampling techniques can reduce user's workload for keystroke pattern registration while maintaining practically allowable error rates of KBS.