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

Showing 201250 of 580 papers

TitleStatusHype
Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style MixtureCode0
CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-AttentionCode0
A War Beyond Deepfake: Benchmarking Facial Counterfeits and CountermeasuresCode0
Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual ManipulationsCode0
2D-Malafide: Adversarial Attacks Against Face Deepfake Detection SystemsCode0
Block shuffling learning for Deepfake DetectionCode0
ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake ImagesCode0
Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set ConditionCode0
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social NetworksCode0
Measuring the Robustness of Audio Deepfake DetectorsCode0
Lip Sync Matters: A Novel Multimodal Forgery DetectorCode0
LoRAX: LoRA eXpandable Networks for Continual Synthetic Image AttributionCode0
Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns InjectionCode0
Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo ConversionCode0
Learning Pairwise Interaction for Generalizable DeepFake DetectionCode0
Individualized Deepfake Detection Exploiting Traces Due to Double Neural-Network OperationsCode0
Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated SamplesCode0
Penny-Wise and Pound-Foolish in Deepfake DetectionCode0
An adversarial attack approach for eXplainable AI evaluation on deepfake detection modelsCode0
Deepfake Detection by Human Crowds, Machines, and Machine-informed CrowdsCode0
BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio DatasetCode0
DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and LocalizationCode0
Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio DeepfakeCode0
How Generalizable are Deepfake Image Detectors? An Empirical StudyCode0
AWARE-NET: Adaptive Weighted Averaging for Robust Ensemble Network in Deepfake DetectionCode0
A Dataless FaceSwap Detection Approach Using Synthetic ImagesCode0
A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake DetectionCode0
GM-DF: Generalized Multi-Scenario Deepfake DetectionCode0
Herd Mentality in Augmentation -- Not a Good Idea! A Robust Multi-stage Approach towards Deepfake DetectionCode0
Deepfake Detection and the Impact of Limited Computing CapabilitiesCode0
Few-Shot Speech Deepfake Detection Adaptation with Gaussian ProcessesCode0
FakeFormer: Efficient Vulnerability-Driven Transformers for Generalisable Deepfake DetectionCode0
Face X-ray for More General Face Forgery DetectionCode0
FakePolisher: Making DeepFakes More Detection-Evasive by Shallow ReconstructionCode0
Extending Information Bottleneck Attribution to Video SequencesCode0
FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap DeepfakesCode0
Deep Convolutional Pooling Transformer for Deepfake DetectionCode0
Decoupling Forgery Semantics for Generalizable Deepfake DetectionCode0
Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model GeneralizationCode0
Exploring Green AI for Audio Deepfake DetectionCode0
Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative AnalysisCode0
PolyGlotFake: A Novel Multilingual and Multimodal DeepFake DatasetCode0
Cross-Domain Local Characteristic Enhanced Deepfake Video Detection0
Cross-Domain Audio Deepfake Detection: Dataset and Analysis0
Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifier0
Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection0
Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors0
Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Features0
Exploiting Style Latent Flows for Generalizing Deepfake Video Detection0
Evading DeepFake Detectors via Adversarial Statistical Consistency0
Show:102550
← PrevPage 5 of 12Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AV-Lip-Sync+Accuracy (%)99.29Unverified
2AvtenetAccuracy (%)98.57Unverified
3FACTORROC AUC97.4Unverified
4RealForensicsROC AUC97.1Unverified
5AVADROC AUC94.5Unverified
6AV-Lip-Sync ModelAccuracy (%)94Unverified
7FTCNROC AUC93.1Unverified
8LipForensicsROC AUC91.1Unverified
9Multimodal Ensemble ModelAccuracy (%)89Unverified
10AD DFDROC AUC88.1Unverified
#ModelMetricClaimedVerifiedStatus
1XceptionNetDF96.36Unverified
2QAD-EAUC0.96Unverified
3EfficientNetB4 + EfficientNetB4ST + B4Att + B4AttSTAUC0.94Unverified
4MARLIN (ViT-L)AUC0.94Unverified
5MARLIN (ViT-B)AUC0.93Unverified
6MARLIN (ViT-S)AUC0.89Unverified
7EfficientNetB4 + EfficientNetB4ST + B4AttSTLogLoss0.33Unverified
#ModelMetricClaimedVerifiedStatus
1Cross Efficient Vision TransformerAUC0.95Unverified
2Efficient Vision TransformerAUC0.92Unverified
3EfficientNetB4 + EfficientNetB4ST + B4AttLogLoss0.46Unverified
#ModelMetricClaimedVerifiedStatus
1STYLE0L99Unverified
#ModelMetricClaimedVerifiedStatus
1FasterThanLiesAUC99.65Unverified
#ModelMetricClaimedVerifiedStatus
1FasterThanLiesAUC1Unverified
#ModelMetricClaimedVerifiedStatus
1FasterThanLiesAUC1Unverified
#ModelMetricClaimedVerifiedStatus
1BA-TFDAUC0.99Unverified