First Round Paper Submission: Jan 31, 2025, 23:59:59 PDT.
Check Submission Section for detailed instructions.
Confirmed! Prof Tal Hassner will be speaker at the UDF workshop. Check Speakers for details.

Deepfake content has seen a significant rise in the number and its impact cannot be ignored. The impact of deepfake content is not limited to any specific purposes and it can be used for several malicious purposes including monetary theft, misleading voters in national elections, pornography, and harassment. The statistics show a tremendous growth in deepfake videos in just a couple of years, every form (text, video, images, and audio) of deepfake content is highly popular on social media platforms, and rising frauds due to the tremendous presence of deepfake content.

Interestingly, deepfake is not limited to any particular form of data modality; hence, we assert that treating a single form of deepfake is not sufficient and provides any partial security. It is interesting to note that existing workshops handling this space tackle image/video-based deepfakes heavily and it has also seen a sharp jump in research papers tackling only image/video-based deepfakes ignoring other modalities of deepfakes. Therefore, through this workshop, we want to bring attention to other forms of deepfakes and encourage researchers to propose solutions to counter other forms of deepfakes as well.

Scope

We invite researchers to combat the deepfake content, one of the primary sources of misinformation in this digital century. Since, we are witnessing the impact of deepfakes on every possible area of society including elections, monetary theft, KYC, and digital identities, detecting deepfakes is critical and urgently needed. This workshop seeks contributions on a variety of topics related to the identification and mitigation of deepfake content, including but not limited to:

  • Image/Video Deepfake Detection
  • Audio Deepfake Detection
  • Text Deepfake Detection
  • Document Deepfake Detection
  • Uni-Modal and Multi-Modal Approaches to Deepfake Generation and Detection
  • Document Liveness Detection
  • Novel and Fair Deepfake Datasets
  • Human Analysis in Detecting the Deepfakes
  • Fairness and Bias in Deepfake Detection

Important Dates

CAI-UDF Workshop will follow a two-round review process. Authors can submit their papers in either Round 1 or Round 2. The main advantage of submitting in Round 1 is that papers may be invited for resubmission in Round 2, allowing authors to revise their work in response to reviewer feedback and make substantial improvements.

  • Full Paper and Supplementary Submission (First Round): Jan 31, 2025
  • Author Notification: Feb 24, 2025
  • Full Paper and Supplementary Submission (Second Round): Mar 10, 2025
  • Acceptance Notice: TBD
  • Camera-Ready Submission: TBD

* All deadlines are based on the PDT time zone.

Speakers

Prof Tal Hassner

Co-founder and CTO
WEIR AI

Tal Hassner         

Tal Hassner is a Co-founder and CTO of WEIR AI; and ex-Meta AI senior applied research lead and ex AWS principal scientist. He is also affiliated with The Open University of Israel, Department of Mathematics and Computer Science where he was an Associate Professor until 2018. From 2015 to 2018, he was a senior computer scientist at the Information Sciences Institute (ISI) and a Visiting Associate Professor at the Institute for Robotics and Intelligent Systems, Viterbi School of Engineering, both at USC, CA, USA, working on the IARPA Janus face recognition project.

His work is mostly related to Computer Vision and Machine Learning. Much of his work relates to digital face processing, including face recognition, facial attribute prediction, face alignment, and 3D reconstruction of face shapes. He also worked on problems related to text image processing (OCR), human action recognition in videos, dense correspondence estimation, feature representation and matching, and more.

He is an Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE-TPAMI) and IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM).

Submission Guidelines

  • You can access the style files and paper template through IEEE Template Selector.
  • Papers should be submitted via the EasyChair portal for CAI.
  • In the EasyChair portal, select the Workshop on Unmasking (Truly) Deepfakes: Not only Video Deepfakes Track.
  • The CAI follows a double-blind review process. The submissions should be anonymous.
  • Paper Length: Long papers should be no more than 6 pages, while abstract paper should not exceed 2 pages, including figures, tables, and references. An additional 2 pages may be included for both types of papers (up to 8 pages for long papers and 4 pages for abstract papers), subject to extra charges.
  • All accepted papers must be presented in person by one of the authors at the conference. Workshop participants are required to pay the standard conference registration fees, which cover access to all sessions, including workshops.
  • Presentations follow the same format as the main conference in terms of types and durations.
  • Accepted workshop papers will be published in the conference proceedings under the workshop section, available online through IEEE, and indexed in IEEE Xplore.
  • For more information, please visit Call for Papers and IEEE CAI Website

Organizers

Akshay Agarwal
Dr. Akshay Agarwal (Lead)

Assistant Professor
IISER Bhopal, India

     
Ketan Kotwal
Dr. Ketan Kotwal

Researcher
Idiap, Switzerland

     
Kartik Thakral
Kartik Thakral

Research Scholar
IIT Jodhpur, India

     
Website for Workshop on Unmasking (Truly) Deepfakes (IEEE CAI, 2025)
© 2024 Ketan Kotwal.