Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics
Not on the map. Why?
Abstract (arXiv)
AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information. The need to develop and evaluate DeepFake detection algorithms calls for large-scale datasets. However, current DeepFake datasets suffer from low visual quality and do not resemble DeepFake videos circulated on the Internet. We present a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process. We conduct a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celeb-DF.
Key facts. Cited by 573 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 64; 2022: 76; 2023: 90; 2024: 100; 2025: 136; 2026: 107.
573 papers.
Sort:
By area:
- 2021Multi-attentional Deepfake Detectioncited by 339
- 2022Detecting Deepfakes with Self-Blended Imagescited by 332
- 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
- 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
- 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
- 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
- 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
- 2023Raising the Cost of Malicious AI-Powered Image Editingcited by 160
- 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
- 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
- 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
- 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
38 more
- 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
- 2021Representative Forgery Mining for Fake Face Detectioncited by 108
- 2021One Shot Face Swapping on Megapixelscited by 105
- 2021Local Relation Learning for Face Forgery Detectioncited by 100
- 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
- 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
- 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
- 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
- 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
- 2021Face Forensics in the Wildcited by 87
- 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 81
- 2021KoDF: A Large-scale Korean DeepFake Detection Datasetcited by 80
- 2023AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Datasetcited by 79
- 2023AltFreezing for More General Video Face Forgery Detectioncited by 78
- 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
- 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
- 2022UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detectioncited by 69
- 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 68
- 2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
- 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
- 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
- 2024Common Sense Reasoning for Deepfake Detectioncited by 64
- 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detectioncited by 60
- 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
- 2024FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistantcited by 59
- 2021Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowdscited by 58
- 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
- 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 58
- 2021Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Featurescited by 57
- 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
- 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
- 2023Multimodal Automated Fact-Checking: A Surveycited by 51
- 2021OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildcited by 50
- 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
- 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
- 2022SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakescited by 49
- 2022Deepfake Detection: A Comprehensive Survey from the Reliability Perspectivecited by 48
- 2024FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledgecited by 48
50 most cited of 573 All 573 (JSON)
- 2026Revisiting Cross-Reconstruction for Generalizable Deepfake Detection1 Oct 2026
- 2026Typographic Attack Against VLM-based AI-generated Image Detection30 Sep 2026
- 2026A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient Statistics30 Sep 2026
- 2026A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System29 Sep 2026
- 2026DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection28 Sep 2026
- 2026DBCF: Dual-Branch Complementary Fusion of Foundation Models for Generalized Deepfake Detection28 Sep 2026
- 2026Trustworthy synthetic visual media: Evidence across the media lifecycle28 Sep 2026
- 2026Dissecting Agentic Forensics: The Role of Triage, Prompting, and Evidence Arbitration in Open-World Fake Image Detection21 Sep 2026
- 2026PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection14 Sep 2026
- 2026Lightweight Generalized DeepFake Face Detection with WAVIE: Wavelet Augmented Vision Intermediate Embeddings13 Sep 2026
- 2026Beyond Ambiguous Visual Cues: Studying Physiological Disruptions and Cross-Modal Inconsistencies in Deepfake Videos11 Sep 2026
- 2026What Makes Adversarial Examples Transfer Across Deepfake Detectors?9 Sep 2026
38 more
- 2026Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection7 Sep 2026
- 2026DF26: We Cannot Tell Fake From Real Anymore7 Sep 2026
- 2026GAN-Blot: A Controllable Structure-Style Synthesis Benchmark for Western Blot Forensics6 Sep 2026
- 2026Adaptive Gated Deepfake Detection for Low-Resolution and Resource-Constrained Environments4 Sep 2026
- 2026Preserving Knowledge across Space and Time for Continual Video Deepfake Detection3 Sep 2026
- 2026Multi-Tool Image Editing Attribution in Facial Forgery2 Sep 2026
- 2026Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic Degradation1 Sep 2026
- 2026Data Diversity, Not Frequency Invariance: A Controlled and Self-Audited Study of Compression-Robust Deepfake Detection26 Aug 2026
- 2026Can Tainted Pixels Expose Deepfake Videos?26 Aug 2026
- 2026DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts24 Aug 2026
- 2026Environment-Invariant Subspace Learning for Generalizable Deepfake Detection18 Aug 2026
- 2026MS-MFAD : Multimodal large language models for Face Anti-spoofing Detection18 Aug 2026
- 2026MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection10 Aug 2026
- 2026Deepfakes and Synthetic Media: Generation, Detection, and Governance7 Aug 2026
- 2026FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection4 Aug 2026
- 2026AdaForensics: Learning A Characteristic-aware Adaptive Deepfake Detector3 Aug 2026
- 2026FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detection3 Aug 2026
- 2026Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning30 Jul 2026
- 2026Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection28 Jul 2026
- 2026Explainable Deepfake Detection Challenge23 Jul 2026
- 2026GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectors21 Jul 2026
- 2026An Explainable FFT-Based Spatial-Frequency Fusion Framework for Deepfake Detection19 Jul 2026
- 2026Emergent Region-Level Facial Correspondence in Frozen Vision Foundation Models15 Jul 2026
- 2026Continuously Evolving Deepfake Detection: An Architecture and Public-Benchmark Evaluation of a Dynamic Detection System14 Jul 2026
- 2026Detecting AI-Generated Video: A Vision-Language Dual-View Survey12 Jul 2026
- 2026Unified Face Attack Detection via Fine-Grained Semantic Guidance9 Jul 2026
- 2026Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors8 Jul 2026
- 2026VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection7 Jul 2026
- 2026SGF-CDNet: A Consistency-Discrepancy Graph Network over Semantic-Geometric Fused Nodes for Face Forgery Detection4 Jul 2026
- 2026The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectors28 Jun 2026
- 2026What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations24 Jun 2026
- 2026When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift17 Jun 2026
- 2026Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection15 Jun 2026
- 2026A Multi-Domain Feature Fusion Framework for Generalizable Deepfake Detection Across Different Generators12 Jun 2026
- 2026The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence6 Jun 2026
- 2026Architecture-Adaptive Uncertainty Fusion for Deepfake Detection4 Jun 2026
- 2026Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation3 Jun 2026
- 2026The DeepSpeak-Agentic Dataset2 Jun 2026
50 newest of 573 All 573 (JSON)
- 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
- 2023Raising the Cost of Malicious AI-Powered Image Editingcited by 160
- 2023Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Modelscited by 36
- 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
- 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
- 2024Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectorscited by 17
- 2024Masked Conditional Diffusion Model for Enhancing Deepfake Detectioncited by 9
- 2024Diffusion Deepfakecited by 8
- 2024Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunitiescited by 7
- 2023Undercover Deepfakes: Detecting Fake Segments in Videoscited by 4
- 2025Fit for Purpose? Deepfake Detection in the Real Worldcited by 4
- 2025Learning Joint ID-Textual Representation for ID-Preserving Image Synthesiscited by 2
12 most cited of 17 All 17 (JSON)
- 2026When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift17 Jun 2026
- 2026Towards High Fidelity Face Swapping: A Comprehensive Survey and New Benchmark27 Apr 2026
- 2026Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection6 Feb 2026
- 2026ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors5 Jan 2026
- 2025Fit for Purpose? Deepfake Detection in the Real World18 Oct 2025
- 2025FreqCross: A Multi-Modal Frequency-Spatial Fusion Network for Robust Detection of Stable Diffusion 3.5 Generated Images1 Jul 2025
- 2025Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis19 Apr 2025
- 2024Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors12 Nov 2024
- 2024Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities25 Apr 2024
- 2024Diffusion Deepfake2 Apr 2024
- 2024Masked Conditional Diffusion Model for Enhancing Deepfake Detection1 Feb 2024
- 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection27 Dec 2023
12 newest of 17 All 17 (JSON)
- 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 68
- 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
- 2024FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistantcited by 59
- 2025Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detectioncited by 20
- 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
- 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Modelscited by 12
- 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challengescited by 6
- 2026MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Modelscited by 4
- 2025Visual Language Models as Zero-Shot Deepfake Detectorscited by 2
- 2025PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attributioncited by 1
- 2026Unleashing Vision-Language Semantics for Deepfake Video Detectioncited by 0
- 2026VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detectioncited by 0
12 most cited of 14 All 14 (JSON)
- 2026Typographic Attack Against VLM-based AI-generated Image Detection30 Sep 2026
- 2026MS-MFAD : Multimodal large language models for Face Anti-spoofing Detection18 Aug 2026
- 2026VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection7 Jul 2026
- 2026Unleashing Vision-Language Semantics for Deepfake Video Detection25 Mar 2026
- 2026MARE: Multimodal Alignment and Reinforcement for Explainable Deepfake Detection via Vision-Language Models28 Jan 2026
- 2025Visual Language Models as Zero-Shot Deepfake Detectors30 Jul 2025
- 2025PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution19 Apr 2025
- 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models19 Mar 2025
- 2025Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection19 Mar 2025
- 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models8 Mar 2025
- 2024FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant19 Aug 2024
- 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges11 Jun 2024
12 newest of 14 All 14 (JSON)
- 2025PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detectioncited by 5
- 2024A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoningcited by 4
- 2025EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoningcited by 2
- 2026VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detectioncited by 1
- 2026Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Modelscited by 0
- 2026VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection15 Apr 2026
- 2026Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models25 Feb 2026
- 2025EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning18 Oct 2025
- 2025PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection30 Sep 2025
- 2024A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning1 Oct 2024
- 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
- 2024La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detectioncited by 8
- 2025SUEDE:Shared Unified Experts for Physical-Digital Face Attack Detection Enhancementcited by 2
- 2026Rethinking Cross-Domain Evaluation for Face Forgery Detection with Semantic Fine-grained Alignment and Mixture-of-Expertscited by 0
- 2026DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Expertscited by 0
- 2026DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts24 Aug 2026
- 2026Rethinking Cross-Domain Evaluation for Face Forgery Detection with Semantic Fine-grained Alignment and Mixture-of-Experts23 Apr 2026
- 2025SUEDE:Shared Unified Experts for Physical-Digital Face Attack Detection Enhancement7 Apr 2025
- 2024La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection23 Aug 2024
- 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection12 Apr 2024
- 2025WMamba: Wavelet-based Mamba for Face Forgery Detectioncited by 2
- 2025WMamba: Wavelet-based Mamba for Face Forgery Detection16 Jan 2025
- 2021Multi-attentional Deepfake Detectioncited by 339
- 2022Detecting Deepfakes with Self-Blended Imagescited by 332
- 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
- 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
- 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
- 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
- 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
- 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
- 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
- 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
- 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
- 2021Representative Forgery Mining for Fake Face Detectioncited by 108
12 most cited of 523 All 523 (JSON)
- 2026Revisiting Cross-Reconstruction for Generalizable Deepfake Detection1 Oct 2026
- 2026A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient Statistics30 Sep 2026
- 2026A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System29 Sep 2026
- 2026DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection28 Sep 2026
- 2026DBCF: Dual-Branch Complementary Fusion of Foundation Models for Generalized Deepfake Detection28 Sep 2026
- 2026Trustworthy synthetic visual media: Evidence across the media lifecycle28 Sep 2026
- 2026PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection14 Sep 2026
- 2026Lightweight Generalized DeepFake Face Detection with WAVIE: Wavelet Augmented Vision Intermediate Embeddings13 Sep 2026
- 2026Beyond Ambiguous Visual Cues: Studying Physiological Disruptions and Cross-Modal Inconsistencies in Deepfake Videos11 Sep 2026
- 2026What Makes Adversarial Examples Transfer Across Deepfake Detectors?9 Sep 2026
- 2026Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection7 Sep 2026
- 2026DF26: We Cannot Tell Fake From Real Anymore7 Sep 2026
12 newest of 523 All 523 (JSON)