The Deepfake Detection Challenge (DFDC) Preview Dataset
Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, Cristian Canton, Ferrer

TL;DR
This paper introduces the Deepfake Detection Challenge (DFDC) preview dataset, a diverse collection of 5,000 videos with facial modifications, designed to advance deepfake detection research and establish evaluation benchmarks.
Contribution
The paper presents a new, diverse deepfake dataset with standardized metrics and baseline models to facilitate progress in deepfake detection research.
Findings
Baseline models achieved measurable detection performance.
Diversity in dataset enhances robustness of detection methods.
Metrics provide standardized evaluation for future research.
Abstract
In this paper, we introduce a preview of the Deepfakes Detection Challenge (DFDC) dataset consisting of 5K videos featuring two facial modification algorithms. A data collection campaign has been carried out where participating actors have entered into an agreement to the use and manipulation of their likenesses in our creation of the dataset. Diversity in several axes (gender, skin-tone, age, etc.) has been considered and actors recorded videos with arbitrary backgrounds thus bringing visual variability. Finally, a set of specific metrics to evaluate the performance have been defined and two existing models for detecting deepfakes have been tested to provide a reference performance baseline. The DFDC dataset preview can be downloaded at: deepfakedetectionchallenge.ai
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection · Generative Adversarial Networks and Image Synthesis · Image Enhancement Techniques
