RECOD Mobile Presentation-Attack Dataset (RECOD-MPAD)
Creators
- 1. University of Campinas
Description
=============
Introduction
The RECOD Mobile Presentation-Attack Dataset (RECOD-MPAD) is intended for the study of presentation attacks (PAs, also known as spoof attempts) to facial recognition systems in mobile devices.
It consists of frames depicting genuine attempts of unlocking a smartphone, as well as two types of presentation attacks: using printouts of the user face; or using electronic displays showing the user's face.
More details can be found in the accompanying paper:
Detecting face presentation attacks in mobile devices with a patch-based CNN and a sensor-aware loss function
Waldir R. Almeida, Fernanda A. Andaló, Rafael Padilha, Gabriel Bertocco, William Dias, Ricardo da S. Torres, Jacques Wainer, Anderson Rocha
PLoS ONE, 2020 (https://doi.org/10.1371/journal.pone.0238058)
This dataset was developed as part of a research project at the RECOD lab of the Institute of Computing, University of Campinas, Brazil.
==========
Statistics
Number of users: 45
Men: 30/45
Glasses: 14/45
Beard: 13/45
Age range: 18-50
=============================
Basic metadata and file names
Name format:
<device>_<session>_<user>_<label>_<frame>
Label:
0: real, genuine access attempt
1: printout attack - recaptured indoors
2: printout attack - recaptured outdoors (more light)
3: screen attack - large display (CCE TV)
4: screen attack - medium-sized display (HP monitor)
Device:
1: motog3
2: xt1572
Session:
1: outdoors natural direct light
2: outdoors natural diffuse light/shadow
3: indoors, top main light
4: indoors, side light (sunlight coming through window or door)
5: indoors, low-light / noisy
Example:
1_5_20_00_0050
======================
Additional information
In each sequence, the volunteers followed the same instructions:
- Hold the phone as if using it normally, but keep close-to-frontal viewing angles
- Rotate slowly (to change lighting and background)
Files
Restricted
The record is publicly accessible, but files are restricted to users with access.
Request access
If you would like to request access to these files, please fill out the form below.
You need to satisfy these conditions in order for this request to be accepted:
Researchers who are interested in downloading and using this dataset are requested to read this agreement, fill up the acceptance form, and send a signed copy to the Representative Licensor before access can be granted.
Link to agreement and form
End-User License Agreement (EULA)
This End User License Agreement (EULA) is granted by the University of Campinas (“hereinafter referred to as Licensor”), Av. Albert Einstein, 1251 Cidade Universitária, Campinas/SP, to the End User. This copy of the RECOD Mobile Presentation Attack Dataset (RECOD-MPAD) is licensed and not sold. This dataset is protected by copyright laws, as well as laws related to other forms of intellectual property. The University of Campinas owns intellectual property rights in the RECOD-MPAD dataset. The Licensee’s license to download, use, copy, or change the RECOD-MPAD dataset is subject to these rights and to all the terms and conditions of this End User License Agreement.
1. Acceptance: You accept and agree to be bound by the terms of this agreement by sending a signed copy of this EULA to the Representative Licensor. You must agree to all of the terms of this agreement before you will be allowed to download the RECOD-MPAD dataset. If you do not agree to all of the terms of this agreement, you must not use or copy the RECOD-MPAD dataset. By accepting this EULA agreement, the End User agrees to strictly respect the conditions set forth herein and to respect all the Brazilian’s laws related to data protection, and identity protection of the volunteers that contributed to creating the RECOD-MPAD dataset.
2. License Grant: This Agreement entitles you to use the RECOD-MPAD dataset. In addition, you may make one or more copies of the RECOD-MPAD dataset, but all copies of the RECOD-MPAD dataset must be on a private (no shared) storage medium. This Agreement does not permit the use of the RECOD-MPAD dataset on a system that allows shared use, on a multiuser network, or on any configuration or system of computers that allows multiple users. Multiple copy use is only allowed if you obtain an appropriate licensing agreement for each user of the RECOD-MPAD dataset. For further information regarding multiple copy licensing of the RECOD-MPAD dataset, please contact the Representative Licensor.
3. Restrictions on Transfer: Without first obtaining the express written consent of the Representative Licensor, you may not assign your rights and obligations under this Agreement, or redistribute, encumber, sell, rent, lease, sublicense, or otherwise transfer your rights to the RECOD-MPAD dataset.
4. Restrictions on Use: You may not permit the use, or copy of the RECOD-MPAD dataset by more than one user. If you hold multiple, validly licensed copies, you may not permit the use, or copy the RECOD-MPAD dataset by more users.
5. Restrictions on Alteration: You may modify the RECOD-MPAD dataset or create any derivative work of the RECOD-MPAD dataset, but you may not transfer in any way, permanently or temporarily, distribute or broadcast the modified or derived dataset without permission of the Representative Licensor.
6. Restrictions on Distribution: Without first obtaining the express written consent of Representative Licensor, you may not transfer in any way, permanently or temporarily, distribute or broadcast all or part of the RECOD-MPAD dataset. For further information regarding the distribution of the RECOD-MPAD dataset, please contact the representative licensor.
7. Publications: You must reference the RECOD-MPAD dataset, or results obtained with it, in publications, including, but are not limited to research papers.
Representative Licensor
Prof. Dr. Anderson de Rezende Rocha
e-mail: anderson.rocha@ic.unicamp.br
Reference
Detecting face presentation attacks in mobile devices with a patch-based CNN and a sensor-aware loss function
Waldir R. Almeida, Fernanda A. Andaló, Rafael Padilha, Gabriel Bertocco, William Dias, Ricardo da S. Torres, Jacques Wainer, Anderson Rocha
(Submitted to PLOS ONE)
Acceptance Form
Full Name:
Title of Position:
Organization Name:
Organization Address:
e-mail:
Date:
Signature:
You are currently not logged in. Do you have an account? Log in here