UserBoost: Generating User-specific Synthetic Data for Faster Enrolment into Behavioural Biometric Systems

TL;DR

This paper introduces a method to generate synthetic user-specific gestures using deep learning, significantly reducing enrolment time in behavioral biometric systems without compromising accuracy.

Contribution

It presents a novel autoencoder-based approach to create diverse synthetic gestures that enhance training efficiency for biometric authentication systems.

Findings

Synthetic gestures improve classification accuracy.

Enrolment gestures reduced by over 40%.

No negative impact on error rates.

Abstract

Behavioural biometric authentication systems entail an enrolment period that is burdensome for the user. In this work, we explore generating synthetic gestures from a few real user gestures with generative deep learning, with the application of training a simple (i.e. non-deep-learned) authentication model. Specifically, we show that utilising synthetic data alongside real data can reduce the number of real datapoints a user must provide to enrol into a biometric system. To validate our methods, we use the publicly available dataset of WatchAuth, a system proposed in 2022 for authenticating smartwatch payments using the physical gesture of reaching towards a payment terminal. We develop a regularised autoencoder model for generating synthetic user-specific wrist motion data representing these physical gestures, and demonstrate the diversity and fidelity of our synthetic gestures. We show that using synthetic gestures in training can improve classification ability for a real-world system. Through this technique we can reduce the number of gestures required to enrol a user into a WatchAuth-like system by more than 40% without negatively impacting its error rates.