Advancing State-of-the-art of Biometrics Presentation Attacks and their Detection
Due to a large surge of illegal access, authentication of access has gained significant attention. Biometrics recognition is one of the most secure metrics towards that goal. While the metric achieved significant performance due to advancement in machine learning and artificial intelligence algorithms, the system is still highly vulnerable against presentation attacks also known as spoofing.
More precisely, a presentation attack refers to the presentation of an artifact or human characteristic to the biometric capture subsystem in a manner that can interfere with the envisioned policy of the biometric system. As the deployment of biometric systems increases, the significance of effective security measures against presentation attacks becomes vital. Therefore, presentation attack detection has received much attention from the computer vision and pattern recognition communities. Due to the recent advances in deep learning and big data analytics, significant research is being performed in the related fields.
In recent years, several research works have been published advancing the knowledge towards the development and detection of the presentation attack instrument. However, the security field is a game of cat and mouse, where one tries to advance the attack, another tries to break the security. Beyond general-purpose classification systems, other examples testify to the existence of adversarial attacks. Security algorithms, such as presentation attack detection algorithms, are found vulnerable and require further attention. Similarly, the new attacks come into the picture such as wax figure faces which makes the earlier deployed detection algorithms less effective.
Therefore, we welcome original research papers making substantial theoretical and practical contributions on robust presentation attack detection in combination with computer vision and machine learning topics, including, but not limited to:
● Novel methodologies on presentation attack detection in visual media
● Studies on novel attacks to biometric systems and solutions
● Zero-shot learning for presentation attack detection
● Deep learning methods for biometric authentication systems using visual media
● Novel datasets and evaluation protocols on spoofing prevention on visual and multimodal biometric systems
● Generative models (e.g. GAN) for presentation attacks
● Novel methods for detecting and preventing presentation attacks
● Adversarial vulnerability of the presentation attack detection algorithms
Keywords: Presentation Attacks, Biometrics, Spoofing, Robustness, Demographic Bias, Adversarial Attacks
Submission Deadlines
| 31 October 2021 | Abstract |
| 15 December 2021 | Manuscript |
WACV2022 :: xAI4Biometrics Workshop :: CALL FOR PAPERS :: Submission deadline on October 04
September 21st, 2021 
Daniela Lopez de Luise
The WACV 2022 2nd Workshop on Explainable & Interpretable Artificial Intelligence for Biometrics (xAI4Biometrics Workshop 2022) intends to promote research on Explainable & Interpretable-AI to facilitate the implementation of AI/ML in the biometrics domain, and specifically to help facilitate transparency and trust.
This workshop will include two keynote talks by:
• Walter J. Scheirer, Notre Dame University, USA
• Speaker TBA
The xAI4Biometrics Workshop 2022 is organized by INESC TEC, Porto, Portugal and co-organized by the European Association for Biometrics (EAB).
For more information please visit http://vcmi.inesctec.pt/xai4biometrics
IMPORTANT DATES
Abstract submission (mandatory): October 04, 2021
Full Paper Submission Deadline: October 11, 2021
Acceptance Notification: November 15, 2021
Camera-ready & Registration: November 19, 2021
Conference: January 04-08, 2022 | Workshop Date: January 04, 2022
TOPICS OF INTEREST
The xAI4Biometrics welcomes works that focus on biometrics and promote the development of:
• Methods to interpret the biometric models to validate their decisions as well as to improve the models and to detect possible vulnerabilities;
• Quantitative methods to objectively assess and compare different explanations of the automatic decisions;
• Methods and metrics to study/evaluate the quality of explanations obtained by post-model approaches and improve the explanations;
• Methods to generate model-agnostic explanations;
• Transparency and fairness in AI algorithms avoiding bias;
• Methods that use post-model explanations to improve the models’ training;
• Methods to achieve/design inherently interpretable algorithms (rule-based, case-based reasoning, regularization methods);
• Study on causal learning, causal discovery, causal reasoning, causal explanations, and causal inference;
• Natural Language generation for explanatory models;
• Methods for adversarial attacks detection, explanation and defense (“How can we interpret adversarial examples?”);
• Theoretical approaches of explainability (“What makes a good explanation?”);
• Applications of all the above including proofs-of-concept and demonstrators of how to integrate explainable AI into real-world workflows and industrial processes.
ORGANIZING COMMITTEES
GENERAL CHAIRS
o Jaime S. Cardoso, INESC TEC and University of Porto, Portugal
o Ana F. Sequeira, INESC TEC, Porto, Portugal
o Arun Ross, Michigan State University, USA
o Peter Eisert, Humboldt University & Fraunhofer HHI
o Cynthia Rudin, Duke University, USA
PROGRAMME CHAIRS
o Christoph Busch, NTNU & Hochschule Darmstadt
o Tiago de Freitas Pereira, IDIAP Research Institute, Switzerland
o Wilson Silva, INESC TEC and University of Porto, Portugal
CONTACT
Ana Filipa Sequeira, PhD (ana.f.sequeira@inesctec.pt)
Assistant Researcher
INESC TEC, Porto, Portugal
Dr.-Ing. Naser Damer
Smart Living & Biometric Technologies
Fraunhofer Institute for Computer Graphics Research IGD
Fraunhoferstr. 5 | 64283 Darmstadt | Germany Tel +49 6151 155-521
Fax +49 6151 155-499 | naser.damer@igd.fraunhofer.de | www.igd.fraunhofer.de
Call for workshop papers
September 21st, 2021 Daniela Lopez de Luise October 2021.
Website: https://wacv2022.thecvf.com/node/88
Tuesday, January 4th 2022
Workshop On Manipulation, Adversarial and Presentation Attacks In Biometrics
Organizers: Kiran Raja, Naser Damer, Raghavendra Ramachandra, Julian Fierrez
Website: https://sites.google.com/view/wacv2022-map-a
XAI4Biometrics – 2nd Workshop on Explainable & Interpretable Artificial
Intelligence for Biometrics
Organizers: Jaime S. Cardoso, Ana F. Sequeira, Arun Ross, Peter Eisert,
Cynthia Rudin
Website: http://vcmi.inesctec.pt/xai4biom_wacv2022/
Video/Audio Quality in Computer Vision
Organizers: Kevin Bowyer, Larry Davis, Zongyi Liu, Yarong Feng
Website: https://sites.google.com/view/wacv2022-workshop-quality-va/home
Human Activity Detection in multi-camera, Continuous, long-duration Video
Organizers: Afzal Godil, Jonathan Fiscus, Yooyoung Lee, Anthony Hoogs,
Reuven Meth
Website: https://actev.nist.gov/workshop/hadcv22
Dealing with the Novelty in Open Worlds
Organizers: Pulkit Kumar, Anubhav, Shu Kong, Christopher Funk, Terrance
Boult, Bill Ferguson, Abhinav Shrivastava
Website: https://www.cs.umd.edu/~pulkit/DNOW_workshop/
Saturday, January 8th 2022
The Third Workshop on Demographic Variations in Performance of
Biometrics and Related Technology
Organizers: Kevin Bowyer, Michael King, Karl Ricanek, Arun Ross, Nisha
Srinivas
Website: https://sites.google.com/trueface.ai/bias-workshop-wacv2022/home
Real-World Surveillance: Applications and Challenges
Organizers: Kamal Nasrollahi, Sergio Escalera Guerrero, Radu Ionescu,
Fahad Shahbaz Khan, Thomas Moeslund, Anthony Hoogs, Shmuel Peleg,
Mubarak Shah
Website: https://vap.aau.dk/rws/
Hazard Perception in Intelligent Vehicles
Organizers: Ardhendu Behera, Venkatesh Babu, Dima Damen, Nik Bessis,
Yonghuai Liu, C. S. Shankar Ram
Website: https://ardhendubehera.github.io/HPIV/index.html
1st Workshop on Computer Vision for Winter Sports
Organizers: Matteo Dunnhofer, Nicola Conci, Christian Micheloni
Website: https://machinelearning.uniud.it/events/CV4WS-2022/Home.html
Workshop on Applications of Computational Imaging
Organizers: Scott McCloskey, Keigo Hirakawa
Website: https://sites.google.com/kitware.com/waci2022/home
1st Call for Participation & registration: MediaEval 2021 Predicting Video Memorability Task
September 21st, 2021 Daniela Lopez de Luise 1st CALL FOR PARTICIPATION & DEVELOPMENT DATA RELEASE
Predicting Video Memorability Task
2021 MediaEval Benchmarking Initiative for Multimedia Evaluation
https://multimediaeval.github.io/editions/2021/tasks/memorability/
*******************************************************
Register to participate by filling in the MediaEval 2021 Registration form: https://docs.google.com/forms/d/e/1FAIpQLSchIcIaSlM1fNeWGCSoSBMR6HS48HKMhWEY151vvCmb5KhO-w/viewform
*******************************************************
Annotations: https://annotator.uk/mediaeval/index.php
*******************************************************
The Predicting Video Memorability Task focuses on the problem of predicting how memorable a video will be. It requires participants to automatically predict memorability scores for videos, which reflect the probability of a video being remembered.
Participants will be provided with an extensive dataset of videos with memorability annotations, and pre-extracted state-of-the-art visual features. The ground truth has been collected through recognition tests, and, for this reason, reflects objective measures of memory performance. In contrast to previous work on image memorability prediction, where memorability was measured a few minutes after memorisation, the dataset comes with short-term and long-term memorability annotations. Because memories continue to evolve in long-term memory, in particular during the first day following memorisation, we expect long-term memorability annotations to be more representative of long-term memory performance, which is used preferably in numerous applications.
*******************************************************
Video-based prediction task
*******************************************************
Participants will be required to train computational models capable of inferring video memorability from visual content. Optionally, descriptive titles attached to the videos may be used. Models will be evaluated through standard evaluation metrics used in ranking tasks.
*******************************************************
Generalization task (optional)
*******************************************************
The aim of the Generalization subtask is to check system performance on other types of video data. Participants will use their systems, trained on one of the two sources of data we propose, to predict the memorability of videos from the testing set of the other source of data. We believe this would provide interesting insights into the performance of the developed systems, given that, while the two sources of data measure memorability in a similar way, the videos may be somewhat different with regards to their content, general subjects or length. As this will be an optional task, participants are not required to participate in it.
Pilot demonstration task (pilot)
*******************************************************
The aim of the Memorability-EEG pilot task is to promote interest in the use of neural signals—either alone, or in combination with other data sources—in the context of predicting video memorability by demonstrating what EEG data can provide. The dataset will be a set of features pre-extracted from the EEG for a subset of videos from task 1. This demonstration pilot will enable interested researchers to see how they could use neural signals without any of the requisite domain knowledge in a future Memorability task, potentially increasing interdisciplinary interest in the subject of memorability, and opening the door to novel EEG-computer vision combined approaches to predicting video memorability.
Pre-selected participants in this pilot demonstration will use the dataset to explore all manners of machine learning and processing strategies to predict video memorability. This will lead to a presentation on their findings, which will ultimately contribute towards the collaborative definition of a fully-fledged task at MediaEval 2022, where participating teams will submit runs and be benchmarked.
***********************
Target communities
***********************
Researchers will find this task interesting if they work in the areas of human perception and scene understanding, such as image and video interestingness, memorability, attractiveness, aesthetics prediction, event detection, multimedia affect and perceptual analysis, multimedia content analysis, machine learning (though not limited to).
***********************
Data
***********************
The first dataset is composed of a subset of 6,000 short videos retrieved from TRECVid 2019 Video to Text dataset [1]. Each video consists of a coherent unit in terms of meaning and is associated with two scores of memorability that refer to its probability to be remembered after two different durations of memory retention. Similar to previous editions of the task [2], memorability has been measured using recognition tests, i.e., through an objective measure, a few minutes after the memorisation of the videos (short term), and then 24 to 72 hours later (long term). The videos are shared under Creative Commons licenses that allow their redistribution. They come with a set of pre-extracted features, such as: Histograms in the HSV and RGB spaces, HOG, LBP, and deep features extracted from AlexNet, VGG and C3D. In comparison to the videos used for this task in 2018 and 2019, the TRECVid videos have much more action happening in them and thus are more interesting for subjects to view.
Additionally, we will open the Memento10k dataset to participants. This dataset contains 10.000 three-second videos depicting in-the-wild scenes, with their associated short term memorability scores, memorability decay values, action labels, and 5 accompanying captions. 7000 videos will be released as a training set, and 1500 will be given for validation. The last 1500 videos will be used as the test set for scoring submissions. The scores are computed with 90 annotations per video on average, and the videos were deafened before being shown to participants. We will also distribute a set of features for each video analogous to the Trecvid set.
***********************
Annotations
***********************
We need more annotations for the dataset. We kindly ask for your help to get more annotations. Please visit the link (https://annotator.uk/mediaeval/index.php) and participate in the funny game to contribute to the dataset and get familiar with the data. Thanks in advance for your contribution
******************************
Workshop
******************************
Participants to the task are invited to present their results during the annual MediaEval Workshop, which will be held in Bergen, Norway with opportunity for online, on 6-8 December 2021. Working notes proceedings are to appear with CEUR Workshop Proceedings (ceur-ws.org).
******************************
Important dates (tentative)
******************************
(open) Participant registration: July
Data release: 15 September
Runs due: 11 November
Working notes papers due: 22 November
MediaEval Workshop: 6-8 December, in Bergen, Norway with opportunity for online participation
***********************
Task coordination
***********************
Alba García Seco de Herrera, <alba.garcia(at)essex.ac.uk>, University of Essex, UK
Rukiye Savran Kiziltepe, <rs16419(at)essex.ac.uk>, University of Essex, UK
Mihai Gabriel Constantin, <cmihaigabriel(at)gmail.com>, University Politehnica of Bucharest, Romania
Bogdan Ionescu, University Politehnica of Bucharest, Romania
Alan Smeaton, Graham Healy, Dublin City University, Ireland
Claire-Hélène Demarty, InterDigital, R&I, France
Sebastian Halder, University of Essex, UK
Ana Matrán-Fernández, University of Essex, UK
Camilo Fosco, Massachusetts Institute of Technology Cambridge, Massachusetts, USA
Lorin Sweeney, Dublin City University, Ireland
Graham Healy, Dublin City University, Ireland
On behalf of the Organizers,
Alba García Seco de Herrera
Dr Alba García Seco de Herrera
Department of Computer Science and Electronic Engineering (CSEE)
University of Essex
https://www.essex.ac.uk/people/garci58409/alba-garcia-seco-de-herrera
Participate in a HCI research project with UAM and win an iPad! Last days! iPad raffle September 20!
September 21st, 2021 Daniela Lopez de Luise We need your help!! We want to obtain a large database with as many users as possible for our research project!
It is very easy to participate. The study consists of carrying out a series of simple tasks that are part of the usual interaction with our mobiles (typing, reading, etc.). The tasks are carried out in less than 2 minutes and are repeated during 4 sessions, with a time frame of at least 1 day between sessions. The data acquired will be completely anonymized in compliance with the EU GDPR.
Participate and enter in the raffle for an iPad. In addition, the more you share the app with your contacts, the more chances you will have to win the iPad. The iPad’s raffle will take place on September 20, so you have the last chances to participate!
Link to the app: LINK
If you can not use Google services in your country, then use this link to download the app installer: LINK
Thank you very much in advance! Please participate and share the app!
In you have any technical problem, you can contact us at: behavepass@uam.es – bidalabuam@gmail.com
Best regards,
The BiDA Lab Team
Autonomous University of Madrid (UAM)
Biometrics and Data Pattern Analytics (BiDA) Lab – ATVS
Escuela Politécnica Superior / School of Engineering
Universidad Autónoma de Madrid – Campus de Cantoblanco
c/ Francisco Tomas y Valiente, 11 – 28049 Madrid (SPAIN)
https://atvs.ii.uam.es/atvs/