Keystroke Biometric Studies on Password and Numeric Keypad Input
Ned Bakelman, John Vincent Monaco, Sung-Hyuk Cha, Charles C. Tappert · 2013
The keystroke biometric classification system described in this study was evaluated on two types of short input - passwords and numeric keypad input. On the password input, the system outperforms 14 other systems evaluated in a previous study using the same raw input data. The three top performing systems in that study had equal error rates between 9.6% and 10.2%. With the classification system developed in this study, equal error rates of 8.7% were achieved on both the features from the previous study and on a new set of features. On the numeric keypad input, the system achieved an equal error rate of 10.5% on the features from the previous study and 6.1% on a new set of features.