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 501–550 of 580 papers

TitleStatusHype
Recap: Detecting Deepfake Video with Unpredictable Tampered Traces via Recovering Faces and Mapping Recovered Faces—0
Recent Advancements In The Field Of Deepfake Detection—0
Reduced Spatial Dependency for More General Video-level Deepfake Detection—0
Replay Attacks Against Audio Deepfake Detection—0
Representation Loss Minimization with Randomized Selection Strategy for Efficient Environmental Fake Audio Detection—0
Retrieval-Augmented Audio Deepfake Detection—0
Robust Deepfake On Unrestricted Media: Generation And Detection—0
Searching for the Fakes: Efficient Neural Architecture Search for General Face Forgery Detection—0
Securing Social Media Against Deepfakes using Identity, Behavioral, and Geometric Signatures—0
Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era—0
Selective Domain-Invariant Feature for Generalizable Deepfake Detection—0
SELFI: Selective Fusion of Identity for Generalizable Deepfake Detection—0
Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis—0
Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style MixtureCode0
XAI-Based Detection of Adversarial Attacks on Deepfake DetectorsCode0
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social NetworksCode0
Penny-Wise and Pound-Foolish in Deepfake DetectionCode0
Towards Interactive Deepfake AnalysisCode0
PolyGlotFake: A Novel Multilingual and Multimodal DeepFake DatasetCode0
2D-Malafide: Adversarial Attacks Against Face Deepfake Detection SystemsCode0
Practical Manipulation Model for Robust Deepfake DetectionCode0
Preserving AUC Fairness in Learning with Noisy Protected GroupsCode0
One-Class Learning with Adaptive Centroid Shift for Audio Deepfake DetectionCode0
Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set ConditionCode0
BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio DatasetCode0
Exploring Green AI for Audio Deepfake DetectionCode0
Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual ManipulationsCode0
Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?Code0
Deepfake Detection by Human Crowds, Machines, and Machine-informed CrowdsCode0
TADA: Training-free Attribution and Out-of-Domain Detection of Audio DeepfakesCode0
DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and LocalizationCode0
CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake DetectionCode0
Diffuse or Confuse: A Diffusion Deepfake Speech DatasetCode0
TAR: Generalized Forensic Framework to Detect Deepfakes using Weakly Supervised LearningCode0
AWARE-NET: Adaptive Weighted Averaging for Robust Ensemble Network in Deepfake DetectionCode0
Towards Quantitative Evaluation of Explainable AI Methods for Deepfake DetectionCode0
Testing Human Ability To Detect Deepfake Images of Human FacesCode0
Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive ForensicsCode0
VoD: Learning Volume of Differences for Video-Based Deepfake DetectionCode0
Measuring the Robustness of Audio Deepfake DetectorsCode0
Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake DetectionCode0
An adversarial attack approach for eXplainable AI evaluation on deepfake detection modelsCode0
Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns InjectionCode0
LoRAX: LoRA eXpandable Networks for Continual Synthetic Image AttributionCode0
Lip Sync Matters: A Novel Multimodal Forgery DetectorCode0
Deepfake Detection and the Impact of Limited Computing CapabilitiesCode0
Learning Pairwise Interaction for Generalizable DeepFake DetectionCode0
Robust AI-Generated Face Detection with Imbalanced DataCode0
Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detectionCode0
Individualized Deepfake Detection Exploiting Traces Due to Double Neural-Network OperationsCode0
Show:102550
← PrevPage 11 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