FRAUD2 - Face Replay Attack UQ Dataset, Version 2

Location

http://www.itee.uq.edu.au/sas/datasets/

FRAUD2 - Description

The FRAUD2 dataset contains the following items:

Videos of objects using a computer tablet screen that displays white light from the screen to illuminate them. The objects consist of a 20 different soft toys, five printed faces on pieces of paper, and five live subjects (same faces as the paper faces).
The illumination from the computer screen is randomly turned on and off to form a digital watermark in the video capture sequence. This watermark is used to determine that the video was captured at a particular point in time (the time when that sequence of light/dark was displayed form the computer screen).

Each object is recorded five times on each of three cameras. The cameras consist of the in-built Microsoft LifeCam on the Microsoft Surface Pro 2 tablet, a Logitech Pro 5000 webcam, and a Logitech Pro 9000 webcam.

Objects are also recorded in each of six different environments, as outlined in the Download section. This results in 300 soft toy videos, 75 paper face videos, and 75 live face videos for each environment.

Each video consists of the following:
- Five frames of no illumination (blank screen on the tablet)
- A single frame of full illumination, as a start signal
- 31 frames of random settings of illumination (full on, or full off)
- Six frames of no illumination (blank screen on the tablet)
This table shows an example of the random illumination sequence that would be observed during the video capture process.

Images are captured using an application that was developed on Ubuntu Linux 13.10 and OpenCV 2.4.9 running on a VMware Player 6.0.4 virtual machine. The VM is hosted by a Microsoft Surface Pro 2 tablet running Windows 8.1 Pro. Individual frames are saved using the DIVX codec, with resolution 640x480@30fps (the actual frame rate varies, as the webcam driver adjusts based upon current lighting conditions, however this will not affect any results).
Ground truth data for each video, detailing the illumination sequence that was used to illuminate the object. Included in this file is an integer representation of the illumination sequence, to assist simple comparison of results. This integer is calculated as the decimal value of the binary representation of the illumination sequence (Dark = 0, Light = 1).
For example, for the illumination sequence "Dark Light Light Light Dark Dark Light", the binary representation is 0111001, producing a decimal result of 57. Note that the actual values will be a maximum of 2³¹.
The results obtained using the techniques developed by the authors for classifying the reflections. These are provided for comparison purposes only.

Licence

The FRAUD2 (Face Replay Attack UQ Dataset, Version 2) and associated data ('Licensed Material') are made available to the scientific community for non-commercial research purposes such as academic research, teaching, scientific publications or personal experimentation. Permission is granted to you (the 'Licensee') to use, copy and distribute the Licensed Material in accordance with the following terms and conditions:

Licensee must include a reference to the following publication in any published work that makes use of the Licensed Material:

Binary Watermarks: A Practical Method to Address Face Recognition Replay Attacks on Consumer Mobile Devices
Daniel F. Smith, Arnold Wiliem, and Brian C. Lovell

IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)

BibTex entry:

@inproceedings{Smith_ISBA_2015,
   author = {Smith, Daniel F. and Wiliem, Arnold and Lovell, Brian C.},
   title = {Binary Watermarks: A Practical Method to Address Face Recognition Replay Attacks on Consumer Mobile Devices},
   booktitle = {IEEE International Conference on Identity, Security and Behavior Analysis (ISBA)},
   publisher = {IEEE},
   year = {2015},
   type = {Conference Proceedings}
}

If the Licensee alters the content of the Licensed Material or creates any derivative work, Licensee must include in the altered Licensed Material or derivative work prominent notices to ensure that any recipients know that they are not receiving the original Licensed Material.
Licensee may not use or distribute the Licensed Material or any derivative work for commercial purposes including but not limited to, licensing or selling the Licensed Material or using the Licensed Material for commercial gain.
The Licensed Material is provided 'AS IS', without any expressed or implied warranties. The authors do not accept any responsibility for errors or omissions in the Licensed Material.
This original licence notice must be retained in all copies or derivatives of the Licensed Material.
All rights not expressly granted to the Licensee are reserved by the authors.

Conference Paper Title

Binary Watermarks: A Practical Method to Address Face Recognition Replay Attacks on Consumer Mobile Devices

Abstract

Mobile devices (laptops, tablets, and smart phones) are ideal for the wide deployment of biometric authentication, such as face recognition. However, their uncontrolled use and distributed management increases the risk of remote compromise of the device by intruders or malicious programs. Such compromises may result in the device being used to capture the user's face image and replay it to gain unauthorized access to their online accounts, possibly from a different device. Replay attacks can be highly automated and are cheap to launch worldwide, as opposed to spoofing attacks which are relatively expensive as they must be tailored to each individual victim. In this paper, we propose a technique to address replay attacks for a face recognition system by embedding a binary watermark into the captured video. Our monochrome watermark provides high contrast between the signal states, resulting in a robust signal that is practical in a wide variety of environmental conditions. It is also robust to different cameras and tolerates relative movements well. In this paper, the proposed technique is validated on different subjects using several cameras in a variety of lighting conditions. In addition, we explore the limitations of current devices and environments that can negatively impact on performance, and propose solutions to reduce the impact of these limitations.

FRAUD2 Reflection Dataset Download

The current version of the FRAUD2 Dataset was uploaded on 06-Feb-2015. There are six .ZIP files, one for each of the following environments:

Environment	Download Size	Filename	Description
Dark	212 Mbytes	FRAUD2-Dark.zip	Darkened room
Office	168 Mbytes	FRAUD2-Office.zip	Indoor office with typical fluorescent lighting
Natural	203 Mbytes	FRAUD2-Natural.zip	Indoor office with lighting turned off, illuminated only by natural sunlight from windows
Cloud	356 Mbytes	FRAUD2-Cloud.zip	Outdoor environment under 100% cloud cover
Shade	581 Mbytes	FRAUD2-Shade.zip	Outdoor environment (no clouds), under 100% shade, but open to the sky
Sunlight	538 Mbytes	FRAUD2-Sunlight.zip	Outdoor environment fully illuminated by 100% direct sunlight

Ethical Clearance

The experiment data involving humans was performed in accordance with the School of ITEE Ethics Approval Number: EC201303SMI.A1.

Contact

Further enquiries can be made to:
{danny döt smith ät uq döt net döt au},
{a döt wiliem ät uq döt edu döt au}, or
{lovell ät itee döt uq döt edu döt au}.

Last updated: 06-Feb-2015