KDPrint: Passive Authentication using Keystroke Dynamics-to-Image Encoding via Standardization

TL;DR

The paper tackles PIN security gaps by enabling passive mobile authentication via keystroke dynamics encoded as images. It introduces a time-series-to-image encoding pipeline that leverages standardized features and touch-location data, paired with a one-class Deep SVDD to identify imposters without extra user actions. On a 17-subject Android dataset, the approach achieves an average accuracy of about $93.2\%$ and an equal-error rate around $0.06$, outperforming several time-series-to-image baselines and prior keystroke methods. This method offers a lightweight, background security layer with practical implications for scalable, nonintrusive mobile authentication, while acknowledging dataset and posture-related limitations and proposing future extensions to other behavioral signals.

Abstract

In contemporary mobile user authentication systems, verifying user legitimacy has become paramount due to the widespread use of smartphones. Although fingerprint and facial recognition are widely used for mobile authentication, PIN-based authentication is still employed as a fallback option if biometric authentication fails after multiple attempts. Consequently, the system remains susceptible to attacks targeting the PIN when biometric methods are unsuccessful. In response to these concerns, two-factor authentication has been proposed, albeit with the caveat of increased user effort. To address these challenges, this paper proposes a passive authentication system that utilizes keystroke data, a byproduct of primary authentication methods, for background user authentication. Additionally, we introduce a novel image encoding technique to capture the temporal dynamics of keystroke data, overcoming the performance limitations of deep learning models. Furthermore, we present a methodology for selecting suitable behavioral biometric features for image representation. The resulting images, depicting the user's PIN input patterns, enhance the model's ability to uniquely identify users through the secondary channel with high accuracy. Experimental results demonstrate that the proposed imaging approach surpasses existing methods in terms of information capacity. In self-collected dataset experiments, incorporating features from prior research, our method achieved an Equal Error Rate (EER) of 6.7%, outperforming the existing method's 47.7%. Moreover, our imaging technique attained a True Acceptance Rate (TAR) of 94.4% and a False Acceptance Rate (FAR) of 8% for 17 users.

Figures (7)

• Figure 1: The overall user authentication process of the proposed system.
• Figure 2: The feature set used in out dataset.
• Figure 3: The example of feature-engineered dataset table and image generated using our proposed method.
• Figure 4: The keystroke dynamics to image encoding result with different scale.
• Figure 5: The results of image encoding for the ideal, real, and impostor cases.