14 datasets found
  1. P

    FaceForensics++ Dataset

    • paperswithcode.com
    • opendatalab.com
    • +1more
    Updated Jun 10, 2021
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Andreas Rössler; Davide Cozzolino; Luisa Verdoliva; Christian Riess; Justus Thies; Matthias Nießner (2021). FaceForensics++ Dataset [Dataset]. https://paperswithcode.com/dataset/faceforensics-1
    Explore at:
    Dataset updated
    Jun 10, 2021
    Authors
    Andreas Rössler; Davide Cozzolino; Luisa Verdoliva; Christian Riess; Justus Thies; Matthias Nießner
    Description

    FaceForensics++ is a forensics dataset consisting of 1000 original video sequences that have been manipulated with four automated face manipulation methods: Deepfakes, Face2Face, FaceSwap and NeuralTextures. The data has been sourced from 977 youtube videos and all videos contain a trackable mostly frontal face without occlusions which enables automated tampering methods to generate realistic forgeries.

  2. P

    FaceForensics Dataset

    • library.toponeai.link
    • opendatalab.com
    • +1more
    Updated Apr 28, 2025
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Andreas Rössler; Davide Cozzolino; Luisa Verdoliva; Christian Riess; Justus Thies; Matthias Nießner (2025). FaceForensics Dataset [Dataset]. https://library.toponeai.link/dataset/faceforensics
    Explore at:
    Dataset updated
    Apr 28, 2025
    Authors
    Andreas Rössler; Davide Cozzolino; Luisa Verdoliva; Christian Riess; Justus Thies; Matthias Nießner
    Description

    FaceForensics is a video dataset consisting of more than 500,000 frames containing faces from 1004 videos that can be used to study image or video forgeries. All videos are downloaded from Youtube and are cut down to short continuous clips that contain mostly frontal faces. This dataset has two versions:

    Source-to-Target: where the authors reenact over 1000 videos with new facial expressions extracted from other videos, which e.g. can be used to train a classifier to detect fake images or videos.

    Selfreenactment: where the authors use Face2Face to reenact the facial expressions of videos with their own facial expressions as input to get pairs of videos, which e.g. can be used to train supervised generative refinement models.

  3. FaceForensics++ Dataset (C23)

    • kaggle.com
    Updated Dec 7, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Xdxd_003 (2024). FaceForensics++ Dataset (C23) [Dataset]. https://www.kaggle.com/datasets/xdxd003/ff-c23/code
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Dec 7, 2024
    Dataset provided by
    Kagglehttp://kaggle.com/
    Authors
    Xdxd_003
    Description

    This is the FaceForensics++ dataset downloaded from original scripts. The dataset contains the following folders: DeepFakeDetection, Deepfakes, Face2Face, FaceShifter, FaceSwap, NeuralTextures, original, csv. Total 7010 files with 7000 mp4 videos (6000 deepfake, 1000 real) and 10 csv files

    Folder Info:

    DeepFakeDetection - 1000 deepfake videos.

    Deepfakes - 1000 deepfake videos.

    Face2Face - 1000 deepfake videos.

    FaceShifter - 1000 deepfake videos.

    FaceSwap - 1000 deepfake videos.

    NeuralTextures - 1000 deepfake videos.

    original - 1000 real videos.

    csv - 10 csv files with metadata about the videos.

    The videos are downloaded at moderate compression with c23 option ( c23 corresponds to H.264 compression at quality 23 (constant rate factor, CRF 23) )

    More about FaceForensics++:

    https://github.com/ondyari/FaceForensics

    http://niessnerlab.org/projects/roessler2018faceforensics.html

    LICENSE:

    https://github.com/ondyari/FaceForensics/blob/master/LICENSE

    Terms of Use:

    https://kaldir.vc.in.tum.de/faceforensics/webpage/FaceForensics_TOS.pdf

  4. f

    Accuracies of FaceForensics++ (HQ) (ACC).

    • plos.figshare.com
    xls
    Updated Dec 13, 2024
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou (2024). Accuracies of FaceForensics++ (HQ) (ACC). [Dataset]. http://doi.org/10.1371/journal.pone.0311366.t003
    Explore at:
    xlsAvailable download formats
    Dataset updated
    Dec 13, 2024
    Dataset provided by
    PLOS ONE
    Authors
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    With the advancement of deep forgery techniques, particularly propelled by generative adversarial networks (GANs), identifying deepfake faces has become increasingly challenging. Although existing forgery detection methods can identify tampering details within manipulated images, their effectiveness significantly diminishes in complex scenes, especially in low-quality images subjected to compression. To address this issue, we proposed a novel deep face forgery video detection model named Two-Stream Feature Domain Fusion Network (TSFF-Net). This model comprises spatial and frequency domain feature extraction branches, a feature extraction layer, and a Transformer layer. In the feature extraction module, we utilize the Scharr operator to extract edge features from facial images, while also integrating frequency domain information from these images. This combination enhances the model’s ability to detect low-quality deepfake videos. Experimental results demonstrate the superiority of our method, achieving detection accuracies of 97.7%, 91.0%, 98.9%, and 90.0% on the FaceForensics++ dataset for Deepfake, Face2Face, FaceSwap, and NeuralTextures forgeries, respectively. Additionally, our model exhibits promising results in cross-dataset experiments.. The code used in this study is available at: https://github.com/hwZHc/TSFF-Net.git.

  5. FaceForensics++ youtube c40 subset from 00 to 49

    • kaggle.com
    Updated Nov 21, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Vittorio Stile (2024). FaceForensics++ youtube c40 subset from 00 to 49 [Dataset]. https://www.kaggle.com/datasets/vittoriostile/faceforensics-youtube-c40-subset-from-00-to-49/code
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Nov 21, 2024
    Dataset provided by
    Kagglehttp://kaggle.com/
    Authors
    Vittorio Stile
    Area covered
    YouTube
    Description

    Dataset

    This dataset was created by Vittorio Stile

    Released under Other (specified in description)

    Contents

  6. faceforensics-datset

    • kaggle.com
    Updated Apr 22, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Siddhant Baiswar (2025). faceforensics-datset [Dataset]. https://www.kaggle.com/datasets/siddhantbaiswar/faceforensics-datset/discussion
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Apr 22, 2025
    Dataset provided by
    Kagglehttp://kaggle.com/
    Authors
    Siddhant Baiswar
    Description

    Dataset

    This dataset was created by Siddhant Baiswar

    Contents

  7. f

    Details of the training parameters.

    • plos.figshare.com
    xls
    Updated Dec 13, 2024
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou (2024). Details of the training parameters. [Dataset]. http://doi.org/10.1371/journal.pone.0311366.t002
    Explore at:
    xlsAvailable download formats
    Dataset updated
    Dec 13, 2024
    Dataset provided by
    PLOS ONE
    Authors
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    With the advancement of deep forgery techniques, particularly propelled by generative adversarial networks (GANs), identifying deepfake faces has become increasingly challenging. Although existing forgery detection methods can identify tampering details within manipulated images, their effectiveness significantly diminishes in complex scenes, especially in low-quality images subjected to compression. To address this issue, we proposed a novel deep face forgery video detection model named Two-Stream Feature Domain Fusion Network (TSFF-Net). This model comprises spatial and frequency domain feature extraction branches, a feature extraction layer, and a Transformer layer. In the feature extraction module, we utilize the Scharr operator to extract edge features from facial images, while also integrating frequency domain information from these images. This combination enhances the model’s ability to detect low-quality deepfake videos. Experimental results demonstrate the superiority of our method, achieving detection accuracies of 97.7%, 91.0%, 98.9%, and 90.0% on the FaceForensics++ dataset for Deepfake, Face2Face, FaceSwap, and NeuralTextures forgeries, respectively. Additionally, our model exhibits promising results in cross-dataset experiments.. The code used in this study is available at: https://github.com/hwZHc/TSFF-Net.git.

  8. f

    Results of cross-database experiments on the Celeb-DF dataset (AUC).

    • plos.figshare.com
    xls
    Updated Dec 13, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou (2024). Results of cross-database experiments on the Celeb-DF dataset (AUC). [Dataset]. http://doi.org/10.1371/journal.pone.0311366.t005
    Explore at:
    xlsAvailable download formats
    Dataset updated
    Dec 13, 2024
    Dataset provided by
    PLOS ONE
    Authors
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    Results of cross-database experiments on the Celeb-DF dataset (AUC).

  9. Ablation study results for branching strategies (ACC).

    • plos.figshare.com
    xls
    Updated Dec 13, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou (2024). Ablation study results for branching strategies (ACC). [Dataset]. http://doi.org/10.1371/journal.pone.0311366.t006
    Explore at:
    xlsAvailable download formats
    Dataset updated
    Dec 13, 2024
    Dataset provided by
    PLOShttp://plos.org/
    Authors
    Hangchuan Zhang; Caiping Hu; Shiyu Min; Hui Sui; Guola Zhou
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    Ablation study results for branching strategies (ACC).

  10. i

    Individualized Deepfake Detection Dataset

    • ieee-dataport.org
    Updated Mar 9, 2025
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Mushfiqur Rahman (2025). Individualized Deepfake Detection Dataset [Dataset]. https://ieee-dataport.org/documents/individualized-deepfake-detection-dataset
    Explore at:
    Dataset updated
    Mar 9, 2025
    Authors
    Mushfiqur Rahman
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    such as FaceForensics++ and DFDC

  11. UNMASKING DEEPFAKES: A DUAL-STAGE TRANSFORMER MODEL FOR DETECTING...

    • zenodo.org
    Updated Jun 4, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Vincent Froom; Vincent Froom (2025). UNMASKING DEEPFAKES: A DUAL-STAGE TRANSFORMER MODEL FOR DETECTING AI-GENERATED FACIAL VIDEOS [Dataset]. http://doi.org/10.5281/zenodo.15593052
    Explore at:
    Dataset updated
    Jun 4, 2025
    Dataset provided by
    Zenodohttp://zenodo.org/
    Authors
    Vincent Froom; Vincent Froom
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    As deepfakes pose increasing threats to media authenticity and public trust, accurate detection mechanisms are vital. This paper proposes a novel dual-stage transformer model for detecting deepfake facial videos. The model combines a spatial attention transformer to capture facial features across individual frames and a contextual consistency transformer to track identity coherence across time. Results from benchmark datasets (FaceForensics++, DFDC) show this architecture significantly outperforms conventional CNNs and RNNs in both accuracy and generalization. This research offers a pathway toward more robust and interpretable video forensics solutions.

  12. O

    WildDeepfake

    • opendatalab.com
    zip
    Updated Oct 1, 2023
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Deakin University (2023). WildDeepfake [Dataset]. https://opendatalab.com/OpenDataLab/WildDeepfake
    Explore at:
    zipAvailable download formats
    Dataset updated
    Oct 1, 2023
    Dataset provided by
    Fudan University
    Deakin University
    License

    https://github.com/deepfakeinthewild/deepfake-in-the-wildhttps://github.com/deepfakeinthewild/deepfake-in-the-wild

    Description

    In recent years, the abuse of a face swap technique called deepfake Deepfake has raised enormous public concerns. Deepfake manipulates deep learning techniques to replace one person's face in a video to someone else's without leaving obvious traces. So far, a large number of deepfake videos (also known as "deepfakes") have been crafted and uploaded to the internet, which calls for the development of effective countermeasures.One promising countermeasure against deepfakes is deepfake detection. Several deepfake datasets have been released to support the training and testing of deepfake detectors, such as DeepfakeDetection and FaceForensics++.While this has greatly advanced deepfake detection, most of the real videos in these datasets are filmed with a few volunteer actors in limited scenes, and the fake videos are crafted by researchers using a few popular deepfake softwares. Detectors developed on these datasets may lose effectiveness when applied to detect the vast variety of deepfake videos in the wild (those uploaded to varies video-sharing websites). To better support detection against real-world deepfakes, in this paper, we introduce a new dataset WildDeepfake, which consists of 7,314 face sequences extracted from 707 deepfake videos that are collected completely from the internet. WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop more effective detectors against real-world deepfakes.We conduct a systematic evaluation of a set of baseline detection networks on both existing and our WildDeepfake datasets, and show that WildDeepfake is indeed a more challenging dataset, where the detection performance can decrease drastically. We also propose two (eg. 2D and 3D) Attention-based Deepfake Detection Networks (ADDNets) to leverage the attention masks on real/fake faces for improved detection. We empirically verify the effectiveness of ADDNets on both existing and WildDeepfake.

  13. P

    DFDC Dataset

    • paperswithcode.com
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Brian Dolhansky; Russ Howes; Ben Pflaum; Nicole Baram; Cristian Canton Ferrer, DFDC Dataset [Dataset]. https://paperswithcode.com/dataset/dfdc
    Explore at:
    Authors
    Brian Dolhansky; Russ Howes; Ben Pflaum; Nicole Baram; Cristian Canton Ferrer
    Description

    The DFDC (Deepfake Detection Challenge) is a dataset for deepface detection consisting of more than 100,000 videos.

    The DFDC dataset consists of two versions:

    Preview dataset. with 5k videos. Featuring two facial modification algorithms. Full dataset, with 124k videos. Featuring eight facial modification algorithms

  14. P

    HFFD Dataset

    • paperswithcode.com
    Updated May 10, 2020
    + more versions
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Zhiqing Guo; Gaobo Yang; Jiyou Chen; Xingming Sun (2020). HFFD Dataset [Dataset]. https://paperswithcode.com/dataset/hffd
    Explore at:
    Dataset updated
    May 10, 2020
    Authors
    Zhiqing Guo; Gaobo Yang; Jiyou Chen; Xingming Sun
    Description

    We build a hybrid fake face (HFF) dataset, which contains eight types of face images. For real face images, three types of face images are randomly selected from three open datasets. They are low-resolution face images from CelebA, high-resolution face images from CelebA-HQ, and face video frames from FaceForensics, respectively. Thus, real face images under internet scenarios are simulated as real as possible. Then, some most representative face manipulation techniques, which include PGGAN and StyleGAN for identity manipulation, Face2Face and Glow for face expression manipulation, and StarGAN for face attribute transfer, are selected to produce fake face images. The HFF dataset is a large fake face dataset, which contains more than 155k face images.

  15. Not seeing a result you expected?
    Learn how you can add new datasets to our index.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
Andreas Rössler; Davide Cozzolino; Luisa Verdoliva; Christian Riess; Justus Thies; Matthias Nießner (2021). FaceForensics++ Dataset [Dataset]. https://paperswithcode.com/dataset/faceforensics-1

FaceForensics++ Dataset

Explore at:
Dataset updated
Jun 10, 2021
Authors
Andreas Rössler; Davide Cozzolino; Luisa Verdoliva; Christian Riess; Justus Thies; Matthias Nießner
Description

FaceForensics++ is a forensics dataset consisting of 1000 original video sequences that have been manipulated with four automated face manipulation methods: Deepfakes, Face2Face, FaceSwap and NeuralTextures. The data has been sourced from 977 youtube videos and all videos contain a trackable mostly frontal face without occlusions which enables automated tampering methods to generate realistic forgeries.

Search
Clear search
Close search
Google apps
Main menu