Efficacy of Typing Pattern Analysis in Identifying Soft Biometric Information and Its Impact in User Recognition

TLDR: This paper uses two leading machine learning approaches: Support Vector Machine with Radial Basis Function (SVM-RBF) and Fuzzy-Rough Nearest Neighbour with Vaguely Quantified Rough Set (FRNN-VQRS) on multiple publicly available authentic and recognized keystroke dynamics datasets to demonstrate the impact of soft biometric traits.

Abstract: Identifying soft biometric traits such as gender, age group, handedness, hand(s) used, typing skill and emotional states from typing pattern and the inclusion of these traits as additional features in user recognitionis a recent research area in order to improve the performance of keystroke dynamics technique. Knowledge-based user authentication with the combination of keystroke dynamics as biometric characteristics relates the issues to user authentication/identification in cloud computing based applications. Our approach is the one way, where the performance of the keystroke dynamics biometricin user recognition can be improved by using soft biometric traits that provides some additional information about the user which can be extracted from the typing pattern on a computer keyboard or touch screen phone. These soft biometric traits have low discriminating power but can be used to enhance the performance of user recognition in accuracy and time efficiency. In this paper, we are interested in using this technique in thestatic keystroke dynamics user authentication system. It has been observed that the age group (18−30/30+or < 18/18+), gender (male/female), handedness (left-handed/right-handed), hand(s) used (one hand/both hands), typing skill (touch/others) and emotional states (Anger/Excitation) can be extracted from the way of typing on a computer keyboard for single predefined text. This soft biometric information from typing pattern as extra features decreases the Equal Error Rate (EER). We have used two leading machine learning approaches: Support Vector Machine with Radial Basis Function (SVM-RBF) and Fuzzy-Rough Nearest Neighbour with Vaguely Quantified Rough Set (FRNN-VQRS) on multiple publicly available authentic and recognized keystroke dynamics datasets. Our approach on CMU keystroke dynamics datasetsindicates the impact of soft biometric traits.