[PDF] The Deepfake Detection Challenge (DFDC) Preview Dataset | Semantic Scholar (2025)

Figures and Tables from this paper

  • figure 1
  • table 1
  • table 2
  • table 3

Topics

Deepfake Detection Challenge (opens in a new tab)Preview Dataset (opens in a new tab)DeepFake (opens in a new tab)Facial Manipulation Techniques (opens in a new tab)DFDC Dataset (opens in a new tab)DeepFake Images (opens in a new tab)Paid Actors (opens in a new tab)Facial Manipulation Detection (opens in a new tab)Deepfake Detection (opens in a new tab)Face Swapping (opens in a new tab)

449 Citations

Detecting Deepfake Videos with Temporal Dropout 3DCNN
    Daichi ZhangChenyu LiFanzhao LinDan ZengShiming Ge

    Computer Science

    IJCAI

  • 2021

A Temporal Dropout 3-Dimensional Convolutional Neural Network (TD-3DCNN) is proposed to detect deepfake videos and can enhance the representation and generalization ability, avoiding model overfitting and improving detecting accuracy.

  • 65
  • PDF
Zoom-DF: A Dataset for Video Conferencing Deepfake
    Geon-Woo ParkEun-Ju ParkSimon S. Woo

    Computer Science

    WDC@AsiaCCS

  • 2022

A new deepfake dataset, Zoom-DF, which can be injected during the remote meeting and video conferencing, to create a sequence of fake participant images, and while most deepfake datasets focus on the face area, this dataset primarily targets for theRemote meeting, and manipulates movements of the participants.

  • 7
Learning to Recognize Patch-Wise Consistency for Deepfake Detection
    Tianchen ZhaoXiang XuMingze XuHui DingYuanjun XiongWei Xia

    Computer Science

    ArXiv

  • 2020

This work proposes a novel representation learning approach for Deepfake detection, called patch-wise consistency learning (PCL), which learns by measuring the consistency of image source features, resulting to representation with good interpretability and robustness to multiple forgery methods.

  • 19
  • Highly Influenced
The DeepFake Detection Challenge Dataset

Although Deep fake detection is extremely difficult and still an unsolved problem, a Deepfake detection model trained only on the DFDC can generalize to real "in-the-wild" Deepfake videos, and such a model can be a valuable analysis tool when analyzing potentially Deepfaked videos.

Improving DeepFake Detection Using Dynamic Face Augmentation
    Sowmen DasArup DattaMd Saiful IslamMd Ruhul Amin

    Computer Science

    ArXiv

  • 2021

Face-Cutout is introduced, a data augmentation method for training Convolutional Neural Networks (CNN), to improve Deep-Fake detection and it is shown that Face-Cutout can be easily integrated with any CNN-based recognition model and improve detection performance.

  • 2
Spatio-Temporal Catcher: A Self-Supervised Transformer for Deepfake Video Detection
    Maosen LiXurong Li Minghao Li

    Computer Science

    ACM Multimedia

  • 2023

It is argued that data quality has become the main bottleneck of current research and a novel spatio-temporal generator that can synthesize various high-quality "fake" videos in large quantities at a low cost is developed, which enables the model to learn more general spatio/temporal representations in a self-supervised manner.

  • 2
A Face Preprocessing Approach for Improved DeepFake Detection
    P. CharitidisGiorgos Kordopatis-ZilosS. PapadopoulosY. Kompatsiaris

    Computer Science

    ArXiv

  • 2020

This work focuses on the impact of dataset preprocessing on the detection accuracy of the DeepFake detection models and proposes a preprocessing step to improve the quality of training datasets for the problem.

SDHF: Spotting DeepFakes with Hierarchical Features
    Tao LiangPeng Chen Jiao Dai

    Computer Science

    2020 IEEE 32nd International Conference on Tools…

  • 2020

It is observed that for the detection of DeepFake videos, three different level forgery features from frame, clip and video can complement each other, and a hierarchical framework is proposed, using 2D convolutional neural networks for frame-level features extraction followed by a 1D Convolutional aggregator to extract clip-level and video- level features.

  • 5
Deepfakes Detection with Automatic Face Weighting
    D. M. MontserratHanxiang Hao E. Delp

    Computer Science

    2020 IEEE/CVF Conference on Computer Vision and…

  • 2020

A method based on convolutional neural networks (CNNs) and recurrent neural Networks (RNNs) that extracts visual and temporal features from faces present in videos to accurately detect manipulations is introduced.

  • 103
  • Highly Influenced
  • [PDF]
Deepfake video detection: YOLO-Face convolution recurrent approach
    Aya IsmailMarwa S. ElpeltagyM. ZakiK. Eldahshan

    Computer Science

    PeerJ Comput. Sci.

  • 2021

A new project is introduced; You Only Look Once Convolution Recurrent Neural Networks (YOLO-CRNNs), to detect deepfake videos, with superiority of the proposed method compared to the state-of-the-art methods.

...

...

10 References

Celeb-DF: A New Dataset for DeepFake Forensics
    Yuezun LiXin YangPu SunH. QiSiwei Lyu

    Computer Science

    ArXiv

  • 2019

A new DeepFake dataset is presented, Celeb-DF, for the development and evaluation of DeepFake detection algorithms, generated using a refined synthesis algorithm that reduces the visual artifacts observed in existing datasets.

  • 149
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
    Andreas RösslerD. CozzolinoL. VerdolivaC. RiessJustus ThiesM. Nießner

    Computer Science

    ArXiv

  • 2018

A novel face manipulation dataset of about half a million edited images (from over 1000 videos) is introduced, which exceeds all existing video manipulation datasets by at least an order of magnitude and introduces benchmarks for classical image forensic tasks, including classification and segmentation.

DeepFakes: a New Threat to Face Recognition? Assessment and Detection
    Pavel KorshunovS. Marcel

    Computer Science

    ArXiv

  • 2018

This paper presents the first publicly available set of Deepfake videos generated from videos of VidTIMIT database, and demonstrates that GAN-generated Deep fake videos are challenging for both face recognition systems and existing detection methods.

Exposing Deep Fakes Using Inconsistent Head Poses
    Xin YangYuezun LiSiwei Lyu

    Computer Science

    ICASSP 2019 - 2019 IEEE International Conference…

  • 2019

This paper proposes a new method to expose AI-generated fake face images or videos based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D head poses are estimated from the face images.

FaceForensics++: Learning to Detect Manipulated Facial Images
    Andreas RösslerD. CozzolinoL. VerdolivaC. RiessJustus ThiesM. Nießner

    Computer Science

    2019 IEEE/CVF International Conference on…

  • 2019

This paper proposes an automated benchmark for facial manipulation detection, and shows that the use of additional domain-specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.

Development of a video tampering dataset for forensic investigation.
    Omar Ismael Al-SanjaryAhmed Abdullah AhmedG. Sulong

    Computer Science

    Forensic science international

  • 2016
  • 63
Artificial Intelligence, Deepfakes and a Future of Ectypes
    L. Floridi

    Art, Computer Science

  • 2018

The art world is full of reproductions. Some are plain replicas, for example the Mona Lisa. Others are fakes or forgeries, like the BVermeers^ painted by Han van Meegeren that sold for $60 million

  • 115
  • PDF
Deep Fakes: A Looming Challenge for Privacy, Democracy, and National Security
    Robert M. ChesneyD. Citron

    Political Science, Computer Science

  • 2018

The aim is to provide the first in-depth assessment of the causes and consequences of this disruptive technological change, and to explore the existing and potential tools for responding to it.

  • 514

Related Papers

Showing 1 through 3 of 0 Related Papers

    [PDF] The Deepfake Detection Challenge (DFDC) Preview Dataset | Semantic Scholar (2025)
    Top Articles
    Latest Posts
    Recommended Articles
    Article information

    Author: Kelle Weber

    Last Updated:

    Views: 6250

    Rating: 4.2 / 5 (73 voted)

    Reviews: 88% of readers found this page helpful

    Author information

    Name: Kelle Weber

    Birthday: 2000-08-05

    Address: 6796 Juan Square, Markfort, MN 58988

    Phone: +8215934114615

    Job: Hospitality Director

    Hobby: tabletop games, Foreign language learning, Leather crafting, Horseback riding, Swimming, Knapping, Handball

    Introduction: My name is Kelle Weber, I am a magnificent, enchanting, fair, joyous, light, determined, joyous person who loves writing and wants to share my knowledge and understanding with you.