Workshop on Deepfakes and Presentation Attacks in Biometrics

Biometric recognition systems are vulnerable to different types of presentation attacks (PAs), where an adversary presents a fabricated artifact or altered trait to biometric sensors. The intent is often to obfuscate one’s own identity, create a synthetic identity, or to spoof another person’s identity. Typically observed attacks include, but are not limited to printed attack, replay attack, makeup attack and 3D mask attack. In order to detect or deflect presentation attacks on biometric systems, numerous Presentation Attack Detection (PAD, aka, anti-spoofing schemes) have been developed in the literature, including sensor-based (e.g., RGB, Depth and IR) and image-based solutions.

With the advent of techniques such as convolutional neural networks (CNNs) and generative adversarial networks (GANs), more sophisticated presentation attacks such as Deepfakes have emerged. Hence, it is imperative to develop effective countermeasures to address these challenges as well. The field of biometric security has attracted great attention in recent years and has heavily investigated in a number of projects including Tabula Rasa (EU project), ODIN (IARPA project) and DARPA MediFor SAVI underlining the need to solutions to defend against these attack vectors.

This workshop in WACV-2020 is being organized to reflect on these specific issues, the impact and countermeasures for biometric systems. The goal of this workshop is to bring experts from computer vision, pattern recognition and image processing fields to advance the state-of-the-art PAD solutions and Deepfake detection solutions.

Papers are invited to report on following topics, but not limited to:

• Novel attack mechanisms
• Novel physical attacks on biometric systems (e.g.,mask attacks).
• Approaches on evaluating the human perception in detecting such attacks
• Algorithmic advancements in detecting attacks
• Detection and mitigation of adversarial attacks
• Presentation Attack Detection (e.g., Face, Fingerprint and Iris )
• Deepfake attacks on biometrics and detection methods.
• Digital Manipulation
• Generalizability of Presentation Attack Detection
• Explainable AI in Presentation Attack
• Multi-modal Presentation Attack Detection
• Novel Presentation Attacks
• Novel Sensor-based Solutions
• Datasets and Evaluations
• Social and Ethical Implications
• Image Forensics
• Forgery Detection

Submission Guidelines:

• Papers presented at WACV workshops will be published as part of the "WACV Workshop Proceedings" and should, therefore, follow the same guideline as the main conference. Workshop papers will be included in IEEE Xplore, but will be indexed separately from the main conference papers. Paper submission guidlines of WACV can be accessed through this link.
• For review, a complete paper should be submitted using the for_review format and the guidelines provided in the author kit. All reviews are double-blind, so please be careful not to include any identifying information including the authors’ names or affiliations.
• Accepted papers will be allocated 8 pages in the proceedings. Please note that References/Bibliography at the end of the paper will NOT count toward the aforementioned page limit. That is, a paper can be up to 8 pages + the references.
• The submission template can be downloaded here.
• Please submit your papers under: https://cmt3.research.microsoft.com/DEEPPAB2020/

Camera-ready Submission Guidelines:

• Please use the following form to submit your camera-ready paper: https://forms.gle/bpTXGWMSXREFcGRR6
• The form will take you through a number of steps, where you will need to fill in some information and upload a compliant and validated camera-ready PDF. Copyright submission will happen in a two-step process: once all authors submit this form, IEEE will reach out to everyone with instructions on how to submit the eCF.

Important Dates

• Workshop: The workshop will take place on WACV 2020 - March 5, 2020
• Full Paper Submission: 15th January, 2020
• Acceptance Notice: 25th January, 2020 (sent)
• Camera-Ready Paper: 10th February, 2020 (23:59 PST)

Program (March 5, 2020) (UPDATED):

• 09:30-09:40 - Opening Remarks - Adam Czajka, University of Notre Dame
• 09:40-10:30 - Keynote – DeepFakes and Detection Challenges - Wael Abd-Almageed, USC Viterbi School of Engineering
• 10:30-11:00 - Coffee Break & Poster Setup
• 11:00-11:20 - IMD2020: A Large-Scale Annotated Dataset Tailored for Detecting Manipulated Images - Babak Mahdian, Czech Academy of Sciences
• 11:20-11:40 - Disrupting Image-Translation-Based DeepFake Algorithms with Adversarial Attacks - Chin-Yuan Yeh, National Taiwan University
• 11:40-12:00 - Syn2Real: Forgery Classification via Unsupervised Domain Adaptation - Kranti Kumar Parida, IIT Kanpur
• 12:00-13:00 - Lunch (on your own) and Poster Viewing
• 13:00-13:20 - Invited talk – Morphed Face Detection: Can residual noise serve as a cue? - Sushma Venkatesh , NTNU (slides can be downloaded here)
• 13:20-14:10 - Keynote – Presentation Attacks and Master Prints - Arun Ross, MSU
• 14:10-14:15 - Closing Remarks – Adam Czajka, University of Notre Dame

Organizing Committee:

• Kiran Raja, NTNU, Norway
• Naser Damer, Fraunhofer IGD, Germany
• Cunjian Chen, Michigan State University, USA
• Antitza Dantcheva, Inria, France
• Adam Czajka, University of Notre Dame, USA
• Hu Han, Chinese Academy of Sciences (CAS), China
• Raghavendra Ramachandra, NTNU, Norway