Learning Human Identity From Motion Patterns

By Natalia Neverova, Christian Wolf, Griffin Lacey, Alex Fridman, Deepak Chandra, Brandon Barbello, Graham W. Taylor. 2015

192 citations recorded by the source corpus.

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 data set of human movements, passively collected by 1500 volunteers using their smartphones daily over several months. We compare several neural architectures for efficient learning of temporal multi-modal data representations, propose an optimized shift-invariant dense convolutional mechanism, and 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. Finally, we demonstrate that the proposed model can also be successfully applied in a visual context.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Communication-Efficient Learning of Deep Networks from Decentralized Data (2016, background): “[29] also discusses the advantages of keeping sensitive user data on device.”
Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, neutral): “Furthermore, the work in [106] used mobile inertial sensor data for motion detection.”
iLGaCo: Incremental Learning of Gait Covariate Factors (2020, background): “[28] build a temporal network for active biometric authentication with data obtained from smartphone sensors.”
FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing (2020, background): “Actually, there exist various similar works before the federated learning, for instance [3], [4], but federated learning emphasizes more on”
Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey (2020, methodology): “Recurrent Neural Network (RNN) were used in [8], [56],”
Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables (2016, background): “First, [Neverova et al. , 2015] investigated a variety of recurrent approaches to identify individuals based on movement data recorded from their mobile phone in a large-scale dataset.”
Mobile sensor data anonymization (2018, methodology): “le devices can reveal private information about users without their awareness. For instance, motion patterns can be used to create fine-grained behavioral profiles of users that reveal their identity [23]. We are interested in designing an on-device privacy-preserving approach to share with apps tra”
Privacy and Utility Preserving Sensor-Data Transformations (2019, background): “Some patterns in raw sensor data may also enable user re-identiﬁcation [6].”