An Agent-Based Modeling Approach to Free-Text Keyboard Dynamics for Continuous Authentication

TL;DR

This paper uses an agent-based model to simulate keyboard typing behaviors for continuous user authentication, revealing that machine learning classifiers like Random Forest can effectively identify users within the same keyboard type but are less effective across different hardware.

Contribution

It introduces an agent-based simulation framework to generate synthetic keystroke data and evaluates machine learning methods for keyboard-based continuous authentication, highlighting hardware's impact on performance.

Findings

Random Forest achieved over 70% accuracy in user recognition within the same keyboard type.

One-Class SVM failed to distinguish individual users effectively.

Keyboard-specific profiles are likely necessary for reliable authentication.

Abstract

Continuous authentication systems leveraging free-text keyboard dynamics offer a promising additional layer of security in a multifactor authentication setup that can be used in a transparent way with no impact on user experience. This study investigates the efficacy of behavioral biometrics by employing an Agent-Based Model (ABM) to simulate diverse typing profiles across mechanical and membrane keyboards. Specifically, we generated synthetic keystroke data from five unique agents, capturing features related to dwell time, flight time, and error rates within sliding 5-second windows updated every second. Two machine learning approaches, One-Class Support Vector Machine (OC-SVM) and Random Forest (RF), were evaluated for user verification. Results revealed a stark contrast in performance: while One-Class SVM failed to differentiate individual users within each group, Random Forest achieved robust intra-keyboard user recognition (Accuracy > 0.7) but struggled to generalize across keyboards for the same user, highlighting the significant impact of keyboard hardware on typing behavior. These findings suggest that: (1) keyboard-specific user profiles may be necessary for reliable authentication, and (2) ensemble methods like RF outperform One-Class SVM in capturing fine-grained user-specific patterns.