• Corpus ID: 219687616

The DeepFake Detection Challenge Dataset

@article{Dolhansky2020TheDD,
  title={The DeepFake Detection Challenge Dataset},
  author={Brian Dolhansky and Joanna Bitton and Ben Pflaum and Jikuo Lu and Russ Howes and Menglin Wang and Cristian Canton-Ferrer},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.07397}
}
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 GAN-based 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… 

Figures and Tables from this paper

Improved Optical Flow Estimation Method for Deepfake Videos

TLDR
This research paper proposes an improved optical flow estimation-based method to detect and expose the discrepancies between video frames, and VGG-16 is the best performing model when used as a backbone for the system.

Work-in-Progress: Detecting Deepfake Videos by Visual-Audio Synchronism

TLDR
A deepfake video detection method based on visual-audio synchronism, which compares the audio stream and the visual stream by an improved siamese neural network, which can achieve the highest accuracy compared with other existing methods is proposed.

Understanding the Security of Deepfake Detection

TLDR
This work performs a systematic measurement study to understand the security of the state-of-the-art deepfake detection methods in adversarial settings, and finds that an attacker can evade a face extractor, and a face classifier trained using deepfakes generated by one method cannot detect deepfake images generated by another method.

Domain General Face Forgery Detection by Learning to Weight

TLDR
This paper argues that different faces contribute differently to a detection model trained on multiple domains, making the model likely to fit domain-specific biases, and proposes the LTW approach based on the meta-weight learning algorithm, which configures different weights for face images from different domains.

A Survey on Deepfake Video Detection

TLDR
It has been revealed that current detection methods are still insufficient to be applied in real scenes, and further research should pay more attention to the generalization and robustness.

iCaps-Dfake: An Integrated Capsule-Based Model for Deepfake Image and Video Detection

TLDR
A new deepfake detection approach, iCaps-Dfake, is proposed that competes with state-of-the-art techniques of deepfake video detection and addresses their low generalization problem.

Deepfake Detection Scheme Based on Vision Transformer and Distillation

TLDR
This paper designs that a CNN features and patchbased positioning model learns to interact with all positions to find the artifact region for solving false negative problem, and proves that the proposed scheme with patch embedding as input outperforms the state-of-the-art using the combined CNN features.

Towards Solving the DeepFake Problem : An Analysis on Improving DeepFake Detection using Dynamic Face Augmentation

TLDR
A simple data augmentation method termed Face-Cutout is proposed, which dynamically cuts out regions of an image using the face landmark information and achieves a reduction in LogLoss on different datasets, compared to other occlusion-based techniques.

Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection

TLDR
This paper analyzes how different training strategies and data augmentation techniques affect CNN-based deepfake detectors when training and testing on the same dataset or across different datasets.

TCSD: Triple Complementary Streams Detector for Comprehensive Deepfake Detection

TLDR
A novel triple complementary streams detector, namely TCSD is proposed, designed to perceive depth information (DI) which is not utilized by previous methods, and two attention-based feature fusion modules are proposed to adaptively fuse information.
...

References

SHOWING 1-10 OF 33 REFERENCES

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

TLDR
This work presents a system that performs lengthy meta-learning on a large dataset of videos, and is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators.

Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics

TLDR
This work presents a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process and conducts a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celebrity-DF.

FaceForensics++: Learning to Detect Manipulated Facial Images

TLDR
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.

DeepFakes: a New Threat to Face Recognition? Assessment and Detection

TLDR
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 on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
TLDR
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.

Contributing data to deepfake detection research

  • Google AI Blog,
  • 2019

The Deepfake Detection Challenge (DFDC) Preview Dataset

TLDR
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.

Media Forensics and DeepFakes: An Overview

  • L. Verdoliva
  • Computer Science
    IEEE Journal of Selected Topics in Signal Processing
  • 2020
TLDR
This review paper aims to present an analysis of the methods for visual media integrity verification, that is, the detection of manipulated images and videos, with special emphasis on the emerging phenomenon of deepfakes, fake media created through deep learning tools, and on modern data-driven forensic methods to fight them.

DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

TLDR
The on-going effort of constructing a large- scale benchmark for face forgery detection is presented, with 60, 000 videos constituted by a total of 17.6 million frames, 10 times larger than existing datasets of the same kind.

FSGAN: Subject Agnostic Face Swapping and Reenactment

TLDR
A novel recurrent neural network (RNN)-based approach for face reenactment which adjusts for both pose and expression variations and can be applied to a single image or a video sequence and uses a novel Poisson blending loss which combines Poisson optimization with perceptual loss.