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 301–350 of 580 papers

TitleStatusHype
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles—0
Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content—0
Towards Benchmarking and Evaluating Deepfake Detection—0
Towards General Deepfake Detection with Dynamic Curriculum—0
Towards generalisable and calibrated synthetic speech detection with self-supervised representations—0
Towards Generalizable Deepfake Detection by Primary Region Regularization—0
Towards Generalizable Deepfake Detection with Spatial-Frequency Collaborative Learning and Hierarchical Cross-Modal Fusion—0
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder—0
Towards General Visual-Linguistic Face Forgery Detection—0
Towards Measuring Fairness in AI: the Casual Conversations Dataset—0
Towards mitigating uncann(eye)ness in face swaps via gaze-centric loss terms—0
Towards Open-world Generalized Deepfake Detection: General Feature Extraction via Unsupervised Domain Adaptation—0
Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View—0
Toward Transdisciplinary Approaches to Audio Deepfake Discernment—0
Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models—0
TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection—0
TruthLens:A Training-Free Paradigm for DeepFake Detection—0
TruthLens: Explainable DeepFake Detection for Face Manipulated and Fully Synthetic Data—0
Two-branch Recurrent Network for Isolating Deepfakes in Videos—0
Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models—0
Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights—0
Understanding the Security of Deepfake Detection—0
Unearthing Common Inconsistency for Generalisable Deepfake Detection—0
Unexploited Information Value in Human-AI Collaboration—0
UniForensics: Face Forgery Detection via General Facial Representation—0
Unlocking the Capabilities of Vision-Language Models for Generalizable and Explainable Deepfake Detection—0
Unmasking Deep Fakes: Leveraging Deep Learning for Video Authenticity Detection—0
Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes—0
Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies—0
Using Deep Learning to Detecting Deepfakes—0
USTC-KXDIGIT System Description for ASVspoof5 Challenge—0
Video Transformer for Deepfake Detection with Incremental Learning—0
Visual Watermarking in the Era of Diffusion Models: Advances and Challenges—0
VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models—0
What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain—0
What's wrong with this video? Comparing Explainers for Deepfake Detection—0
When Handcrafted Features and Deep Features Meet Mismatched Training and Test Sets for Deepfake Detection—0
Why Do Facial Deepfake Detectors Fail?—0
The Deepfake Detection Dilemma: A Multistakeholder Exploration of Adversarial Dynamics in Synthetic Media—0
0-1 laws for pattern occurrences in phylogenetic trees and networks—0
Limits of Deepfake Detection: A Robust Estimation Viewpoint—0
Multiple Contexts and Frequencies Aggregation Network forDeepfake Detection—0
ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection—0
MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark—0
A3:Ambiguous Aberrations Captured via Astray-Learning for Facial Forgery Semantic Sublimation—0
AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge—0
A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations—0
ADD 2022: the First Audio Deep Synthesis Detection Challenge—0
ADD 2023: Towards Audio Deepfake Detection and Analysis in the Wild—0
Advancing High Fidelity Identity Swapping for Forgery Detection—0
Show:102550
← PrevPage 7 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