BioMoTouch: Touch-Based Behavioral Authentication via Biometric-Motion Interaction Modeling

2026-04-08

AI Summary

Existing touch-based authentication methods rely solely on behavioral signals, neglecting the multidimensional nature of touch interactions, which compromises robustness in complex adversarial and real-world scenarios. This work proposes BioMoTouch, a novel framework that jointly models users’ finger physiological structure and dynamic touch behavior for the first time. By fusing data from capacitive touchscreens and inertial sensors, BioMoTouch explicitly learns their interaction to construct a unified biometric representation, achieving highly robust authentication without requiring additional hardware. Evaluated under realistic usage conditions with 38 participants, the system attains a balanced accuracy of 99.71% and an equal error rate of 0.27%. Furthermore, it demonstrates strong resilience against diverse attacks, with false acceptance rates consistently below 0.90%.

Abstract

Touch-based authentication is widely deployed on mobile devices due to its convenience and seamless user experience. However, existing systems largely model touch interaction as a purely behavioral signal, overlooking its intrinsic multidimensional nature and limiting robustness against sophisticated adversarial behaviors and real-world variations. In this work, we present BioMoTouch, a multi-modal touch authentication framework on mobile devices grounded in a key empirical finding: during touch interaction, inertial sensors capture user-specific behavioral dynamics, while capacitive screens simultaneously capture physiological characteristics related to finger morphology and skeletal structure. Building upon this insight, BioMoTouch jointly models physiological contact structures and behavioral motion dynamics by integrating capacitive touchscreen signals with inertial measurements. Rather than combining independent decisions, the framework explicitly learns their coordinated interaction to form a unified representation of touch behavior. BioMoTouch operates implicitly during natural user interactions and requires no additional hardware, enabling practical deployment on commodity mobile devices. We evaluate BioMoTouch with 38 participants under realistic usage conditions. Experimental results show that BioMoTouch achieves a balanced accuracy of 99.71% and an equal error rate of 0.27%. Moreover, it maintains false acceptance rates below 0.90% under artificial replication, mimicry, and puppet attack scenarios, demonstrating strong robustness against partial-factor manipulation.

Problem

• touch-based authentication
• behavioral biometrics
• multimodal sensing
• adversarial robustness
• mobile security

Innovation

• multimodal authentication
• biometric-motion interaction
• touchscreen sensing
• behavioral dynamics
• physiological biometrics