H-MOG Dataset

This website contains dataset files for A Multimodal Data Set for Evaluating Continuous Authentication Performance in Smartphones.

Introduction

We performed a large-scale user study to collect a wide spectrum of signals about user behaviors on smartphones, including touch, gesture, and pausality of the user, as well as movement and orientation of the phone. This dataset has been used to evaluate a continuous authentication modality named H-MOG in smartphones.

A data collection tool for Android phones was developed to record real-time touch, sensor and key press data invoked by user’s interaction with the phone. Data from three usage scenarios on smartphones were recorded: (1) document reading; (2) text production; (3) navigation on a map to locate a destination.

100 volunteers were recruited for a large-scale data collection. When a volunteer logs into the data collection tool, the volunteer is randomly assigned a reading, writing, or map navigation session. For each session, the volunteer either sits or walks to finish the tasks. One session lasts about 5 to 15 minutes, and each volunteer is expected to perform 24 sessions (8 reading sessions, 8 writing sessions, and 8 map navigation sessions). In total, each volunteer in our experiments contributed about 2 to 6 hours of behavior traits. The data have been completely anonymized.

Cite the Papers

Qing Yang, Ge Peng, David T. Nguyen, Xin Qi, Gang Zhou, Zdeňka Sitová, Paolo Gasti, and Kiran S. Balagani. A Multimodal Data Set for Evaluating Continuous Authentication Performance in Smartphones. In Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems (SenSys ‘14). ACM, New York, NY, USA, 358-359. DOI: 10.1145/2668332.2668366

Readers can also check our research work HMOG: New Behavioral Biometric Features for Continuous Authentication of Smartphone Users.

Zdeňka Sitová, Jaroslav Šeděnka, Qing Yang, Ge Peng, Gang Zhou, Paolo Gasti, Kiran S. Balagani. HMOG: New Behavioral Biometric Features for Continuous Authentication of Smartphone Users. In IEEE Transactions on Information Forensics and Security, vol.11, no.5, pp.877-892, May 2016. DOI: 10.1109/TIFS.2015.2506542

Files

The dataset can be downloaded from the following link. You agree to the Terms of Use for H-MOG Dataset to download and use the files.

Terms of Use for H-MOG Dataset

You need to read and agree to the following Terms of Use to download and use the H-MOG dataset.

Terms of Use for H-MOG Dataset

1. Definitions

The following terms, unless the context requires otherwise, have the following meanings:

“Data Team”: means the employees and students at the College of William and Mary who are working on the H-MOG dataset;

“H-MOG Dataset”: means the large-scale data set about smartphone usage collected by the Data Team;

“Licensee”, “You”, “Your”, “Yours”: means the person or entity acquiring a license hereunder for access to and use of the H-MOG Dataset.

2. Grant of License

The College of William and Mary hereby grants to You a non-exclusive, non-transferable, revocable license to use the H-MOG Dataset solely for Your non-commercial, educational, and research purposes only, but without any right to copy or reproduce, publish or otherwise make available to the public or communicate to the public, sell, rent or lend the whole or any constituent part of the H-MOG Dataset thereof. The H-MOG Dataset shall not be redistributed without the express written prior approval of the College of William and Mary You agree to respect the privacy of those human subjects whose smartphone usage behavior data are included in the H-MOG Dataset. Do not attempt to reverse the anonymization process to identify specific identifiers including, without limitation, names, postal address information, telephone numbers, e-mail addresses, social security numbers, and biometric identifiers. You agree not to reverse engineer, separate or otherwise tamper with the H-MOG Dataset so that data can be extracted and used outside the scope of that permitted in this Agreement.

You agree to acknowledge the source of the H-MOG Dataset in all of Your publications and presentations based wholly or in part on the H-MOG Dataset. You agree to provide a disclaimer in any publication or presentation to the effect that the College of William and Mary does not bear any responsibility for Your analysis or interpretation of H-MOG Dataset.

You agree and acknowledge that the College of William and Mary may hold, process, and store any personal data submitted by You for validation and statistical purposes and for the purposes of the administration and management of H-MOG Dataset. You agree that any personal data submitted by You is accurate to the best of his or her knowledge.

The College of William and Mary provides the H-MOG Dataset “AS IS,” without any warranty or promise of technical support, and disclaims any liability of any kind for any damages whatsoever resulting from use of the H-MOG Dataset .

THE COLLLEGE OF WILLIAM AND MARY MAKES NO WARRANTIES, EXPRESS OR IMPLIED WITH RESPECT TO THE H-MOG DATASET, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, WHICH ARE HEREBY EXPRESSLY DISCLAIMED.

Your acceptance and use of the H-MOG Dataset binds you to the terms and conditions of this License as stated herein.