2 October 2023, Room W07

All times are in CET.

8:30 AM Welcome and introduction
Introduction to the Workshop
DFAD Chairs: L. Baraldi, D. Kangin, T. Glaser, P. Angelov, R. Cucchiara

Introduction to the ELSA DeepFake Detection Challenge
Lorenzo Baraldi (University of Modena and Reggio Emilia)
8:35 AM ELSA DeepFake Challenge presentations
Presentation of the top submissions to the EU ELSA DeepFake Dataset (developed by UNIMORE and Leonardo SpA)

Challenge presentation (L. Baraldi)

First place: Boosting Deepfake Detection with Data Augmentation and DCT
Davide Alessandro Coccomini (ISTI-CNR), Giuseppe Amato (ISTI-CNR), Fabrizio Falchi (ISTI-CNR), Claudio Gennaro (ISTI-CNR)

Second place: MCA-Net: Multimodal Co-Attention Based Network for Detecting AI-Generated Images
Jiache Zhang (Shanghai Jiao Tong University), Xiaohong Liu (Shanghai Jiao Tong University), Xiufeng Song (Shanghai Jiao Tong University), Qirui Li (Shanghai Jiao Tong University), Xiao Guo (Michigan State University), Yihan Wang (Shanghai Jiao Tong University), Zihan Zhang (Shanghai Jiao Tong University), Shilin Wang (Shanghai Jiao Tong University), Guangtao Zhai (Shanghai Jiao Tong University)
8:50 AM Oral presentation: Online Detection of AI-Generated Images
David C. Epstein (Adobe Inc.); Ishan Jain (Adobe Inc); Oliver Wang (Adobe Inc); Richard Zhang (Adobe Inc)
9:05 AM Oral Presentation: TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization
Soumyaroop Nandi (University of Southern California); Prem Natarajan (Amazon); Wael Abd-Almageed (University of Southern California)
9:20 AM Oral presentation: Revisiting Generalizability in Deepfake Detection: Improving Metrics and Stabilizing Transfer
Sarthak Kamat (UC Berkeley); Shruti Agarwal (UC Berkeley); Trevor Darrell (UC Berkeley); Anna Rohrbach (UC Berkeley)
9:35 AM Oral presentation: Interpretable-through-prototypes deepfake detection for diffusion models
Agil Aghasanli (Lancaster University); Dmitry Kangin (Lancaster University); Plamen Angelov (Lancaster University)
9:50 AM Oral presentation: Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning
Pranav Balaji (BITS Pilani); Abhijit Das (BITS Pilani); Srijan Das (University of North Carolina Charlotte); Antitza Dantcheva (INRIA)
10:05 AM Poster Session
FIVA: Facial Video and Image Anonymization and Anonymization Defense
Felix Rosberg (Berge Consulting); Eren Erdal Aksoy (Halmstad University); Cristofer Englund (Halmstad University); Fernando Alonso-Fernandez (Halmstad University)

A Comprehensive Framework for Evaluating Deepfake Generators: Dataset, Metrics Performance, and Comparative Analysis
Sahar Husseini (Eurecom); Jean-Luc Dugelay (France)

WaterLo: Protect Images from Deepfakes Using Localized Semi-Fragile Watermark
Nicolas BEUVE (INSA Rennes); Wassim Hamidouche (INSA Rennes); Olivier Deforges (IETR, Rennes)

Undercover Deepfakes: Detecting Fake Segments in Videos
Sanjay Saha (National University of Singapore); Rashindrie D Perera (University of Melbourne); Sachith H Seneviratne (University of Melbourne); Tamasha Malepathirana (University of Melbourne); Sanka Rasnayaka (National University of Singapore); Deshani Geethika (University of Melbourne); Terence Sim (NUS); Saman Halgamuge (University of Melbourne)

Learning Interpretable Forensic Representations via Local Window Modulation
Sowmen Das (University of Cambridge); Mohammad Ruhul Amin (Fordham University)

Deepfakes signatures Detection in the Handcrafted Features Space
Hamadene Assia (Morsli Abdallah University); abdeldjalil Ouahabi (Tours France); Abdenour Hadid (Sorbonne University Abu Dhabi)
10:35 AM Coffee Break
11:10 AM Invited Talk: An AI Whodunnit: Following Image Manipulation Clues to their Source
Tal Hassner (Meta)
11:45 AM Invited Talk: Sustainable DeepFake Detection, Watermarking, and Personalized Disinformation
Mario Fritz (CISPA)
12:20 PM Invited Talk: Between Illusion and Reality: Guiding AI to Generate IdentityPreserving Images
Naomi Ken Korem (Lightricks)
12:55 PM Closing remarks