2020
DOI: 10.48550/arxiv.2006.07397
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

The DeepFake Detection Challenge (DFDC) Dataset

Abstract: Deepfakes are a recent off-the-shelf manipulation technique that allows anyone to swap two identities in a single video. In addition to Deepfakes, a variety of GANbased face swapping methods have also been published with accompanying code. To counter this emerging threat, we have constructed an extremely large face swap video dataset to enable the training of detection models, and organized the accompanying DeepFake Detection Challenge (DFDC) Kaggle competition. Importantly, all recorded subjects agreed to par… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
201
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 105 publications
(203 citation statements)
references
References 19 publications
1
201
0
1
Order By: Relevance
“…Public information from social networks can be used to create realistic fake videos capable to spoof a FRS, e.g., by means of a replay attack. Recent examples of DeepFake video databases are Celeb-DF [58] and DFDC [20]. DeepFake techniques are evolving very fast, with their outputs becoming more and more realistic each day, so countermeasuring them is a very challenging problem [87,44].…”
Section: Other Attacksmentioning
confidence: 99%
“…Public information from social networks can be used to create realistic fake videos capable to spoof a FRS, e.g., by means of a replay attack. Recent examples of DeepFake video databases are Celeb-DF [58] and DFDC [20]. DeepFake techniques are evolving very fast, with their outputs becoming more and more realistic each day, so countermeasuring them is a very challenging problem [87,44].…”
Section: Other Attacksmentioning
confidence: 99%
“…The ForgeryNet Challenge is hosted on the CodaLab platform 3 . After registering on the ForgeryNet Challenge, teams are required to upload their prediction files to the Co-daLab platform for the ranking.…”
Section: Platformmentioning
confidence: 99%
“…In this paper, the definition of the term "face forgery" refers to an image or a video containing modified identity, expressions or attribute(s) with a learning-based approach, distinguished with 1) a so-called "Cheap-Fakes"[8] that are created with off-the-shelf softwares without learnable components and 2) "DeepFakes" that only refer to manipulations with swapped identities[3] 2. Workshop website: https://sense-human.github.io/.3 Challenge website: https://competitions.codalab.org/ competitions/33386.…”
mentioning
confidence: 99%
“…Over the past few years, face forgery methods have achieved significant success and received lots of attention in the computer vision community (Thies et al 2015;Rossler et al 2019;Dolhansky et al 2020;Gu et al 2021). As such techniques can generate high-quality fake videos that are even indistinguishable for human eyes, they can easily be abused by malicious users to cause severe societal problems or political threats.…”
Section: Introductionmentioning
confidence: 99%
“…Early works (Afchar et al 2018;Stehouwer et al 2019;Dolhansky et al 2020) treat face forgery detection as a binary classification problem and use the convolutional neural network (CNN) to distinguish the authenticity of the face. These methods achieve considerable performance in the intra-domain scenario, where the training and test sets manifest similar data distributions.…”
Section: Introductionmentioning
confidence: 99%