SOTAVerified

DeepFake Detection

DeepFake Detection is the task of detecting fake videos or images that have been generated using deep learning techniques. Deepfakes are created by using machine learning algorithms to manipulate or replace parts of an original video or image, such as the face of a person. The goal of deepfake detection is to identify such manipulations and distinguish them from real videos or images.

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

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 580 papers

TitleStatusHype
DeepFakes and Beyond: A Survey of Face Manipulation and Fake DetectionCode4
DeepFake-O-Meter v2.0: An Open Platform for DeepFake DetectionCode3
UCF: Uncovering Common Features for Generalizable Deepfake DetectionCode3
DeepfakeBench: A Comprehensive Benchmark of Deepfake DetectionCode3
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake DetectionCode3
DF40: Toward Next-Generation Deepfake DetectionCode3
UnMarker: A Universal Attack on Defensive Image WatermarkingCode3
Common Sense Reasoning for Deepfake DetectionCode3
Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A SurveyCode3
Preserving Fairness Generalization in Deepfake DetectionCode2
C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake DetectionCode2
Unlocking the Hidden Potential of CLIP in Generalizable Deepfake DetectionCode2
SafeEar: Content Privacy-Preserving Audio Deepfake DetectionCode2
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakesCode2
Exposing the Deception: Uncovering More Forgery Clues for Deepfake DetectionCode2
Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake DetectionCode2
LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake DetectionCode2
MARLIN: Masked Autoencoder for facial video Representation LearnINgCode2
Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face DetectorCode2
Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake DetectionCode2
SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal ModelCode2
The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake AudioCode2
Faster Than Lies: Real-time Deepfake Detection using Binary Neural NetworksCode2
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable DiffusionCode2
Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024Code2
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space LearningCode2
Detecting Deepfakes with Self-Blended ImagesCode2
Audio Deepfake Detection with Self-Supervised XLS-R and SLS ClassifierCode2
Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingCode2
Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local SimilaritiesCode2
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and LocalizationCode2
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo BenchmarkCode2
Detecting and Grounding Multi-Modal Media ManipulationCode2
Detecting and Grounding Multi-Modal Media Manipulation and BeyondCode2
1M-Deepfakes Detection ChallengeCode2
Detecting music deepfakes is easy but actually hardCode2
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation LearningCode2
A Continual Deepfake Detection Benchmark: Dataset, Methods, and EssentialsCode1
Deepfake Network Architecture AttributionCode1
Analyzing Fairness in Deepfake Detection With Massively Annotated DatabasesCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
Contrastive Learning of Global-Local Video RepresentationsCode1
Combining EfficientNet and Vision Transformers for Video Deepfake DetectionCode1
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and OutlookCode1
CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive LearningCode1
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image DetectorsCode1
Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learningCode1
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake DetectionCode1
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial ExamplesCode1
Contrastive Pseudo Learning for Open-World DeepFake AttributionCode1
Show:102550
← PrevPage 1 of 12Next →
All datasetsFakeAVCelebFaceForensicsDFDC1CIFAKE: Real and AI-Generated Synthetic ImagesCOCOFakeDFFDLAV-DF

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AV-Lip-Sync+Accuracy (%)99.29—Unverified
2AvtenetAccuracy (%)98.57—Unverified
3FACTORROC AUC97.4—Unverified
4RealForensicsROC AUC97.1—Unverified
5AVADROC AUC94.5—Unverified
6AV-Lip-Sync ModelAccuracy (%)94—Unverified
7FTCNROC AUC93.1—Unverified
8LipForensicsROC AUC91.1—Unverified
9Multimodal Ensemble ModelAccuracy (%)89—Unverified
10AD DFDROC AUC88.1—Unverified
#ModelMetricClaimedVerifiedStatus
1XceptionNetDF96.36—Unverified
2QAD-EAUC0.96—Unverified
3EfficientNetB4 + EfficientNetB4ST + B4Att + B4AttSTAUC0.94—Unverified
4MARLIN (ViT-L)AUC0.94—Unverified
5MARLIN (ViT-B)AUC0.93—Unverified
6MARLIN (ViT-S)AUC0.89—Unverified
7EfficientNetB4 + EfficientNetB4ST + B4AttSTLogLoss0.33—Unverified
#ModelMetricClaimedVerifiedStatus
1Cross Efficient Vision TransformerAUC0.95—Unverified
2Efficient Vision TransformerAUC0.92—Unverified
3EfficientNetB4 + EfficientNetB4ST + B4AttLogLoss0.46—Unverified
#ModelMetricClaimedVerifiedStatus
1STYLE0L99—Unverified
#ModelMetricClaimedVerifiedStatus
1FasterThanLiesAUC99.65—Unverified
#ModelMetricClaimedVerifiedStatus
1FasterThanLiesAUC1—Unverified
#ModelMetricClaimedVerifiedStatus
1FasterThanLiesAUC1—Unverified
#ModelMetricClaimedVerifiedStatus
1BA-TFDAUC0.99—Unverified