The DeepFake Detection Challenge (DFDC) Dataset

Dolhansky, Brian; Bitton, Joanna; Pflaum, Ben; Lu, Jikuo; Howes, Russ; Wang, Menglin; Ferrer, Cristian Canton

doi:10.48550/arxiv.2006.07397

Cited by 105 publications

(203 citation statements)

References 19 publications

Supporting

Mentioning

201

Contrasting

Unclassified

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%

Introduction to Presentation Attack Detection in Face Biometrics and Recent Advances

Hernandez-Ortega¹,

Fiérrez²,

Morales³

et al. 2021

Preprint

View full text Add to dashboard Cite

The main scope of this chapter is to serve as an introduction to face presentation attack detection, including key resources and advances in the field in the last few years. The next pages present the different presentation attacks that a face recognition system can confront, in which an attacker presents to the sensor, mainly a camera, a Presentation Attack Instrument (PAI), that is generally a photograph, a video, or a mask, to try to impersonate a genuine user.First, we make an introduction of the current status of face recognition, its level of deployment, and its challenges. In addition, we present the vulnerabilities and the possible attacks that a face recognition system may be exposed to, showing that way the high importance of presentation attack detection methods.We review different types of presentation attack methods, from simpler to more complex ones, and in which cases they could be effective. Then, we summarize the most popular presentation attack detection methods to deal with these attacks.Finally, we introduce public datasets used by the research community for exploring vulnerabilities of face biometrics to presentation attacks and developing effective countermeasures against known PAIs.

show abstract

Section: Other Attacksmentioning

confidence: 99%

Introduction to Presentation Attack Detection in Face Biometrics and Recent Advances

Hernandez-Ortega¹,

Fiérrez²,

Morales³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

ForgeryNet -- Face Forgery Analysis Challenge 2021: Methods and Results

He¹,

Shen²,

Shao³

et al. 2021

Preprint

View full text Add to dashboard Cite

The rapid progress of photorealistic synthesis techniques has reached a critical point where the boundary between real and manipulated images starts to blur. Recently, a mega-scale deep face forgery dataset, ForgeryNet which comprised of 2.9 million images and 221,247 videos has been released. It is by far the largest publicly available in terms of data-scale, manipulations (7 image-level approaches, 8 video-level approaches), perturbations (36 independent and more mixed perturbations) and annotations (6.3 million classification labels, 2.9 million manipulated area annotations and 221,247 temporal forgery segment labels). This paper reports methods and results in the ForgeryNet: Face Forgery Analysis Challenge 2021 which employs the ForgeryNet benchmark. The model evaluation is conducted offline on the private test set. A total of 186 participants registered for the competition, and 11 teams made valid submissions. We will analyze the top ranked solutions and present some discussion on future work directions.

show abstract

“…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%

Dual Contrastive Learning for General Face Forgery Detection

Sun¹,

Yao²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns. Previous works always formulate face forgery detection as a classification problem based on cross-entropy loss, which emphasizes category-level differences rather than the essential discrepancies between real and fake faces, limiting model generalization in unseen domains. To address this issue, we propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which specially constructs positive and negative paired data and performs designed contrastive learning at different granularities to learn generalized feature representation. Concretely, combined with the hard sample selection strategy, Inter-Instance Contrastive Learning (Inter-ICL) is first proposed to promote task-related discriminative features learning by especially constructing instance pairs. Moreover, to further explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces by constructing local-region pairs inside instances. Extensive experiments and visualizations on several datasets demonstrate the generalization of our method against the state-of-the-art competitors.

show abstract

The DeepFake Detection Challenge (DFDC) Dataset

Cited by 105 publications

References 19 publications

Introduction to Presentation Attack Detection in Face Biometrics and Recent Advances

Introduction to Presentation Attack Detection in Face Biometrics and Recent Advances

ForgeryNet -- Face Forgery Analysis Challenge 2021: Methods and Results

Dual Contrastive Learning for General Face Forgery Detection

Contact Info

Product

Resources

About