[visionlist] [CFP] DFF-2026: Deepfake Forensics Workshop @ ACM Multimedia 2026

[Georgia Fargetta]

Apologize for multiple copies





DFF-2026 Workshop - ACM Multimedia 2026





Dear Colleagues,

We invite you to submit your scientific research to the second edition of our Deepfake Forensics: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media Workshop, held in conjunction with ACM Multimedia 2026 (https://2026.acmmm.org/)



DFF-2026: https://iplab.dmi.unict.it/mfs/acm-dff-ws-2026/



Workshop - Overview

We are living in an era where convincing fake multimedia content can be generated in seconds from a simple text prompt, and detecting it is becoming one of the most pressing challenges in the research community.

The creation and manipulation of multimedia content has long been a central concern in the multimedia community. However, recent advances in AI and generative modeling have radically changed the scale, realism, and accessibility of media manipulation, to the point where highly convincing forgeries can be produced with minimal effort, sometimes through simple text prompts. This has significant social, legal, and security consequences, as manipulated and synthetic media are increasingly exploited for disinformation, fraud, non-consensual content, and the potential fabrication of digital evidence. In this landscape, multimedia forensics is becoming both more critical and more challenging: the task is no longer about spotting low-quality forgeries, but reliably analyzing highly realistic manipulations across heterogeneous generation pipelines, and attributing synthetic content to specific models or tools. The field is further complicated by adversarial machine learning and counter-forensic strategies, which expose the limited generalization and vulnerability of existing detection systems.

This workshop aims to consolidate and advance research on the forensic analysis of manipulated and AI-generated multimedia content, including images, videos, and audio, and addressing the full spectrum of challenges ranging from detection and localization to attribution, robustness, explainability, and legal implications. The workshop is designed to cover both the analysis of existing manipulation and generation techniques and the study of new synthesis and editing methods, with the goal of understanding how different manipulation pipelines affect forensic traces and the reliability of detection systems. Particular attention will be focused on adversarial machine learning, which currently represents one of the main threats to the robustness of existing detectors, and to the evaluation of forensic methods in realistic scenarios, such as content uploaded and reshared on social media platforms or processed through typical chains of compression, re-encoding, and post-processing used by online services.

Moreover, the workshop also addresses the design and study of new generative and manipulation methods not only as objects of analysis, but also as experimental tools to identify novel generative traces, explore new attack strategies, and gain a deeper understanding of the continuously evolving capabilities of modern synthesis and editing pipelines. This approach is essential to drive the development of more robust, generalizable, and real-world-oriented detection and attribution methods, avoiding purely reactive solutions tied to specific models or artifacts.



Topics of interest include (but are not limited to):

  *   Detection and localization of manipulated and AI-generated content in images, video, and audio
  *   Multimodal forensic analysis of synthetic and manipulated media
  *   Attribution of generative models, editing tools, and manipulation pipelines
  *   Trace-based forensic analysis of multimedia manipulations and synthetic content
  *   Robustness and generalization of forensic detectors under distribution shifts and real-world conditions
  *   Adversarial machine learning and counter-forensic attacks against multimedia forensic systems
  *   Evaluation of forensic methods in real-world and social-media-like processing pipelines
  *   Dataset design, bias analysis, and benchmarking for synthetic and manipulated media
  *   Explainability and interpretability in multimedia forensic analysis
  *   Passive and active authentication and content provenance verification methods
  *   Generative models and AI-based tools for multimedia content synthesis, editing, and fully synthetic data generation, and their implications for multimedia forensics
  *   Legal, ethical, and regulatory aspects of manipulated and AI-generated media





Important Dates

  *   Workshop paper submission: 16.07.2026
  *   Notification to Authors: 06.08.2026
  *   Camera ready: 20.08.2026
  *   Author Registration: 20.08.2026
  *   Workshop: 10.11.2026 – 14.11.2026





Best Paper Award:

A Best Paper Award will be presented at the Workshop to recognize the most outstanding and innovative research contribution.





Instruction for authors

Paper Format

  *   Submitted papers (.pdf format) must use the ACM Article Template (https://www.acm.org/publications/proceedings-template).
  *   Please remember to add Concepts and Keywords.
  *   Please use the template in traditional double-column format to prepare your submissions. For example, word users should use Word Interim Template, and LaTeX users should use sample-sigconf-authordraft template.
  *   When using sample-sigconf-authordraft Latex template, for submission and review of manuscript you could use the following documentclass command instead of the example provided in the template: \documentclass[sigconf, screen, review, anonymous]{acmart}
  *   Please ensure that you submit your papers subscribing to this format for full consideration during the review process.
  *   Paper Length: Up to 8 pages + 2 additional pages for references



Participants can submit paper through OpenReview plataform.
https://openreview.net/group?id=acmmm.org/ACMMM/2026/Workshop/DFF#tab-your-consoles





Chairs

  *   Luca Guarnera, Research Fellow, luca.guarnera at unict.it<mailto:luca.guarnera at unict.it> (Department of Mathematics and Computer Science, University of Catania, Italy)
  *   Francesco Guarnera, Research Fellow, francesco.guarnera at unict.it<mailto:francesco.guarnera at unict.it> (Department of Mathematics and Computer Science, University of Catania, Italy)

Co-Chairs

  *   Sebastiano Battiato, Full Professor, sebastiano.battiato at unict.it<mailto:sebastiano.battiato at unict.it> (Department of Mathematics and Computer Science, University of Catania, Italy)
  *   Giovanni Puglisi, Associate Professor, puglisi at uinca.it<mailto:puglisi at uinca.it> (Department of Mathematics and Computer Science, University of Cagliari, Italy)
  *   Zahid Akhtar, Associate Professor, akhtarz at sunypoly.edu<mailto:akhtarz at sunypoly.edu> (State University of New York Polytechnic Institute, USA)
  *   Fernando Pérez-González, Full Professor, fperez at gts.uvigo.es<mailto:fperez at gts.uvigo.es> (School of Telecommunication Engineering, University of Vigo, Spain)

Track Chair

  *   Claudio Vittorio Ragaglia, PhD Student, claudio.ragaglia at phd.unict.it<mailto:claudio.ragaglia at phd.unict.it> (Department of Mathematics and Computer Science, University of Catania, Italy)





Main Contact

  *   Name: Luca Guarnera, Francesco Guarnera
  *   Email: workshop.dff at gmail.com<mailto:workshop.dff at gmail.com>





Workshop Web-site

https://iplab.dmi.unict.it/mfs/acm-dff-ws-2026/





We look forward to receiving your contributions and seeing you at ACM MM 2026!






-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20260701/aafc4659/attachment.htm>