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

Abstract

We present our on-going effort of constructing a large-scale benchmark for face forgery detection. The first version of this benchmark, DeeperForensics-1.0, represents the largest face forgery detection dataset by far, with 60,000 videos constituted by a total of 17.6 million frames, 10 times larger than existing datasets of the same kind. Extensive real-world perturbations are applied to obtain a more challenging benchmark of larger scale and higher diversity. All source videos in DeeperForensics-1.0 are carefully collected, and fake videos are generated by a newly proposed end-to-end face swapping framework. The quality of generated videos outperforms those in existing datasets, validated by user studies. The benchmark features a hidden test set, which contains manipulated videos achieving high deceptive scores in human evaluations. We further contribute a comprehensive study that evaluates five representative detection baselines and make a thorough analysis of different settings.

CVPR 2020. Project page: https://liming-jiang.com/projects/DrF1/DrF1.html

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Instance Normalization: The Missing Ingredient for Fast Stylization
• MesoNet: a Compact Facial Video Forgery Detection Network
• Semi-Supervised Learning with Deep Generative Models
• Exposing DeepFake Videos By Detecting Face Warping Artifacts
• DeepFakes: a New Threat to Face Recognition? Assessment and Detection
• The Deepfake Detection Challenge (DFDC) Preview Dataset

Cited by in corpus (17)

• Media Forensics and DeepFakes: an overview
• Combining EfficientNet and Vision Transformers for Video Deepfake Detection
• Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
• FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset
• Generalizing Face Forgery Detection with High-frequency Features
• DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices
• AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
• Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues
• Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features
• HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
• KoDF: A Large-scale Korean DeepFake Detection Dataset
• DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
• An Examination of Fairness of AI Models for Deepfake Detection
• Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
• Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
• The eyes know it: FakeET -- An Eye-tracking Database to Understand Deepfake Perception
• One Shot Face Swapping on Megapixels