Workshop Description
The rapid advancements in deep learning, particularly in generative models such as Generative Adversarial Networks (GANs) and Diffusion Models (DM), have significantly improved the quality and realism of synthetic media, commonly referred to as deepfakes. While these technologies unlock creative possibilities, they simultaneously raise critical concerns regarding digital content authenticity. Deepfake generation and detection are now at the core of multimedia forensics, requiring robust and generalizable methods to identify manipulated content effectively.
This workshop aims to bring together researchers and practitioners from diverse fields, including computer vision, multimedia forensics and adversarial machine learning, to explore emerging challenges and solutions in deepfake detection, attribution, recognition and counter-forensic strategies. Specifically, it will address the limitations of current detection models in generalizing to real-world scenarios, the interpretability of forensic results, and the risks posed by synthetic content. Additionally, the workshop will promote discussions on dataset biases, multimodal deepfake analysis, the forensic ballistics of synthetic media, and the legal and ethical implications of deepfake technology, including regulatory challenges and forensic admissibility in court. Through keynote presentations, research paper presentations, and panel discussions, the workshop will provide a comprehensive overview of state-of-the-art deepfake research while promoting interdisciplinary collaborations to address this pressing societal issue.
Chairs
- Luca Guarnera, Research Fellow, luca.guarnera@unict.it (Department of Mathematics and Computer Science, University of Catania, Italy)
- Francesco Guarnera, Research Fellow, francesco.guarnera@unict.it (Department of Mathematics and Computer Science, University of Catania, Italy)
Main Contact
- Name : Claudio Vittorio Ragaglia
- Email : workshop.dff@gmail.com
- Address : Dipartimento di Matematica e Informatica Cittadella Universitaria - Viale A. Doria 6 – Italy.
Co-Chairs
- Sebastiano Battiato, Full Professor, sebastiano.battiato@unict.it (Department of Mathematics and Computer Science, University of Catania, Italy)
- Giovanni Puglisi, Associate Professor, puglisi@unica.it (Department of Mathematics and Computer Science, University of Cagliari, Italy)
- Zahid Akhtar, Associate Professor, akhtarz@sunypoly.edu (State University of New York Polytechnic Institute, USA)
Track Co-Chairs
- Mirko Casu, PhD Student, , mirko.casu@phd.unict.it (Department of Mathematics and Computer Science, University of Catania, Italy)
- Orazio Pontorno, PhD Student, orazio.pontorno@phd.unict.it (Department of Mathematics and Computer Science, University of Catania, Italy)
- Claudio Vittorio Ragaglia, PhD Student, claudio.ragaglia@phd.unict.it (Department of Mathematics and Computer Science, University of Catania, Italy)
Program Committee
Roberto Caldelli (Universitas Mercatorum)
Giulia Orrú (University of Cagliari)
Rafael Oliveira Ribeiro (Aston University)
Lorenzo Catania (University of Catania)
Salome Cholokashvili (National Forensics Bureau)
Giovanni Lo Monaco (University of Hertfordshire)
Omar Gouda (University of Sharjah)
Dario Allegra (University of Catania)
Mariami Rogava (Lepl Levan Samkharauli National Forensics Bureau of Georgia)
Massimo Orazio Spata (University of Catania)
Davide Ghiani (University of Cagliari)
Alessia Rondinella (University of Catania)
Simone Carta (University of Cagliari)
Andrea Di Pierno (Institute for Advanced Studies Lucca)
Roberto Casula (University of Cagliari)
Francesco Rundo (University of Catania)
Simone Maurizio La Cava (University of Cagliari)
Carlo Augusto Bachschmidt (University of Urbino)
Lea Uhlenbrock (Friedrich-Alexander-Universität Erlangen-Nürnberg)
Roberto Leotta (iCTLab)
Important dates
Participants can submit paper through OpenReview plataform. The link for submission is the following:
https://openreview.net/group?id=acmmm.org/ACMMM/2025/Workshop/DFF#tab-your-consoles
https://openreview.net/group?id=acmmm.org/ACMMM/2025/Workshop/DFF#tab-your-consoles
Motivation
Deepfake technology presents one of the most significant challenges to digital media trustworthiness. The ability to generate hyper-realistic synthetic media threatens the credibility of online information, fuels misinformation campaigns, and poses ethical and legal dilemmas. Despite rapid advancements in deepfake detection, current methods miss of generalization, robustness, and interpretability. Furthermore, malicious actors actively seek to evade forensic detection through adversarial perturbations and counter-forensic methods.
This workshop aligns with ACM Multimedia 2025 by addressing the multimedia community’s urgent need for innovative and scalable solutions to detect, attribute, and mitigate deepfake threats. It also contributes to discussions on dataset development, adversarial robustness, and the interplay between AI-generated content and their applications. The interdisciplinary nature of this problem necessitates a comparison location between multimedia researchers and forensic analysts making this workshop a timely and essential addition to the conference.
Topics
- Deepfake Detection on Images, Video, and Audio
- Multimodal Deepfake Detection
- Deepfake Model Recognition and Attribution
- Forensic Ballistics for Deepfake Analysis
- Adversarial Forensics and Counter-Forensic Techniques
- Generative Models for Deepfake Creation
- Multimodal Datasets for Deepfake Detection and Generation
- Explainability and Interpretability in AI Forensics
- Passive Deepfake Authentication Methods
- Active Deepfake Authentication Methods
- Legal and Ethical Implications of Deepfakes: Detection, Regulation and Accountability
