DFAD 2024: Workshop and Challenge on DeepFake Analysis and Detection at CVPR 2024
On June 17, 2024, the second Workshop and Challenge on DeepFake Analysis and Detection (DFAD) took place in Seattle, in conjunction with CVPR 2024, organized within the ELSA project.
As generative models become more realistic, detecting generated content requires methods that generalize to models unseen during training. The workshop collected new approaches to understanding and detecting fake data, and hosted the ELSA DeepFake Challenge, based on the ELSA DeepFake dataset developed by UNIMORE and Leonardo SpA.
Programme
| 13:00 – 13:05 | Welcome and introduction to the ELSA DeepFake Detection ChallengeLorenzo Baraldi |
| 13:05 – 13:15 | Presentations of the top challenge submissions |
| 13:15 – 13:45 | Deep Fakes: quo vadis? A review of past, current and future of manipulated mediaCristian Canton Ferrer, Head of Responsible AI at Meta |
| 13:45 – 14:15 | Keynote talkRita Cucchiara, University of Modena and Reggio Emilia |
| 14:30 – 15:30 | Oral presentations |
| 15:30 – 16:00 | Keynote talkShiran Ganor, Clarity |
| 16:00 – 17:00 | Poster session |
Times are in Seattle local time.
Organizers
Lorenzo Baraldi (University of Modena and Reggio Emilia), Alessandro Nicolosi (Leonardo SpA), Dmitry Kangin and Plamen Angelov (Lancaster University), Tamar Glaser and Tal Hassner (Meta AI).
An archived copy of the workshop website is available.