Learning Human Identity from Motion Patterns

TL;DR

This paper investigates the use of deep neural networks to identify individuals based on their natural movement patterns captured by mobile sensors, proposing new models and a large dataset for biometric authentication.

Contribution

It introduces the first large-scale dataset of human motion from smartphones and proposes a novel dense convolutional RNN for active biometric authentication.

Findings

Human kinematics encode identifiable user information

The proposed models outperform existing methods in authentication accuracy

Motion-based biometrics can enhance multi-modal security systems

Abstract

We present a large-scale study exploring the capability of temporal deep neural networks to interpret natural human kinematics and introduce the first method for active biometric authentication with mobile inertial sensors. At Google, we have created a first-of-its-kind dataset of human movements, passively collected by 1500 volunteers using their smartphones daily over several months. We (1) compare several neural architectures for efficient learning of temporal multi-modal data representations, (2) propose an optimized shift-invariant dense convolutional mechanism (DCWRNN), and (3) incorporate the discriminatively-trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems.