Free-Text Keystroke Dynamics for User Authentication

TL;DR

This paper introduces a novel approach for user authentication using free-text keystroke dynamics, employing image-like transition matrices and deep learning models to improve accuracy.

Contribution

It presents a new feature engineering method generating image-like transition matrices and demonstrates the effectiveness of CNN and hybrid CNN-RNN models for keystroke-based authentication.

Findings

CNN with cutout achieves top results

Hybrid CNN-RNN outperforms previous methods

Image-like transition matrices are effective features

Abstract

In this research, we consider the problem of verifying user identity based on keystroke dynamics obtained from free-text. We employ a novel feature engineering method that generates image-like transition matrices. For this image-like feature, a convolution neural network (CNN) with cutout achieves the best results. A hybrid model consisting of a CNN and a recurrent neural network (RNN) is also shown to outperform previous research in this field.