Awesome Deepfakes Detection

<small>(image from internet)</small>

A collection list of Deepfakes Detection related datasets, tools, papers, and code. If this list helps you on your research, a star will be my pleasure :)

If you want to contribute to this list, welcome to send me a pull request or contact me :)

This repository only collects papers related to Deepfake Detection. If you are also interested in Deepfakes generation, please refer to: Awesome Deepfakes.

Datasets
Competitions
Tools
Recent Conference Papers
Survey
Spatiotemporal Based
Frequency Based
Generalization
Interpretability
Human-Decision
Localization
Multi-modal Based
Biological Signal
Robustness
Fairness
Fingerprint/Watermark
Identity-Related
Adversarial Attack
Real Scenario
Anomaly Detection
Self-Supervised Learning
Source Model Attribution
Multiclass Classification
Federated Learning
Knowledge Distillation
Meta-Learning
Depth Based

Datasets

Video Datasets

UADFV: Exposing Deep Fakes Using Inconsistent Head Poses. Paper
EBV: In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking. Paper Download
Deepfake-TIMIT: DeepFakes: a New Threat to Face Recognition? Assessment and Detection. Paper Download
DFFD: On the Detection of Digital Face Manipulation. Paper Download
DeepfakeDetection: Download
Celeb-DF (v1): Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics. Paper Download
Celeb-DF (v2): Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics. Paper Download
DFDC: The DeepFake Detection Challenge (DFDC) Dataset. Paper Download
FaceForensic++: FaceForensics++: Learning to Detect Manipulated Facial Images. Paper Download
FFIW-10K: Face Forensics in the Wild. Paper Download
Deeper Forensic-1.0: DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection. Paper Download
Wild Deepfake: WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection. Paper Download
ForgeryNet: ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis. Paper Download
WLDR: Protecting World Leaders Against Deep Fakes. Paper
FakeAVCeleb: FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset. Paper Download

	Real Videos	Fake Videos	Year	Note
UADFV	49	49	2018	focus on head pose
EBV	-	49	2018	focus on eye blinking
Deepfake-TIMIT	320	640	2018	GAN-Based methods
DFFD	1,000	3000	2019	mutiple SOTA methods
DeepfakeDetection	363	3,068	2019	collect from actors with publicly available generation methods
Celeb-DF (v2)	590	5639	2019	high quality
DFDC	23,564	104,500	2019	DFDC competition on Kaggle
FaceForensic++	1,000	5,000	2019	five different generation methods
FFIW-10K	10,000	10,000	2019	mutiple faces in one frame
WLDR	-	-	2019	person of interest video from Youtube
DeeperForensics-1.0	50,000	10,000	2020	add real-world perturbations
Wild-Deepfake	3,805	3,509	2021	collect from Internet
ForgeryNet	99,630	121,617	2021	8 video-level generation methods, add perturbations
FakeAVCeleb	500	19,500	2021	audio-visual multi-modalies dataset

Image Datasets

DFFD: On the Detection of Digital Face Manipulation. Paper Download
iFakeFaceDB: GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection. Paper Download
100k Faces Generated by AI (Online): Download
DFGC: DFGC 2021: A DeepFake Game Competition. Paper Dowload
ForgeryNet: ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis. Paper Download

	Real Images	Fake Images	Year	Note
DFFD	58,703	240,336	2019	mutiple SOTA methods
iFakeFaceDB	-	87,000 (StyleGAN)	2020	generated by StyleGAN
100k Faces	-	100,000 (StyleGAN)	2021	generated by StyleGAN
DFGC	1,000	N*1,000	2021	DFGC 2021 competition, fake images generated by users
ForgeryNet	1,438,201	1,457,861	2021	7 image-level generation methods, add perturbations

Competitions

Name	Link	Year	Note
Deepfake Detection Challenge	Website	2019	1. video-level detection.<br>2. use DFDC datasets.<br/> 3. the first worldwide competition.<br/> 4. more than 2,000 teams participated.
DeepForensics Challenge	Website	2020	1. video-level detection.<br/> 2. use DeeperForensics-1.0 datasets.<br/> 3. simulates real-world scenarios.
Deepfake Game Competition	Website	2021	1. both image-level generation and video-level detection track.<br/> 2. use Celeb-DF(v2) datasets.
Face Forgery Analysis Challenge	Website	2021	1. both image-level and video-level detection track.<br/> 2. addtional temporal localization track.<br/> 3. use ForgeryNet dataset.

Tools

Sensity: Website
Deepware: Website
Baidu Security: Website
DeepReal: Website

Recent Conference Papers

CVPR

Exploiting Style Latent Flows for Generalizing Video Deepfake Detection, CVPR 2024: Paper
AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection, CVPR 2024: Paper
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection, CVPR 2024: Paper
Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection, CVPR 2024: Paper Github
LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection, CVPR 2024: Paper Github
Preserving Fairness Generalization in Deepfake Detection, CVPR 2024: Paper Github
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization, CVPR 2023: Paper Github
Implicit Identity Driven Deepfake Face Swapping Detection, CVPR 2023: Paper
AltFreezing for More General Face Forgery Detection, CVPR 2023: Paper
AUNet: Learning Relations Between Action Units for Face Forgery Detection, CVPR 2023: Paper
Dynamic Graph Learning with Content-guided Spatial-Frequency Relation Reasoning for Deepfake Detection, CVPR 2023: Paper
TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization, CVPR 2023: Paper Github
Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection, CVPR 2023: Paper Github
Towards Universal Fake Image Detectors That Generalize Across Generative Models, CVPR 2023: Paper Github
DF-Platter: Multi-Face Heterogeneous Deepfake Dataset, CVPR 2023: Paper
Self-Supervised Video Forensics by Audio-Visual Anomaly Detection, CVPR 2023: