mlsanityData to 7 Oct 2026

ExDDV: A New Dataset for Explainable Deepfake Detection in Video

arXiv 2503.14421 ↗First posted 18 Mar 2025cs.CV cs.AI cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vulnerable to deepfake-based fraud and misinformation. To this end, we introduce ExDDV, the first dataset and benchmark for Explainable Deepfake Detection in Video. ExDDV comprises around 5.4K real and deepfake videos that are manually annotated with text descriptions (to explain the artifacts) and clicks (to point out the artifacts). We evaluate a number of vision-language models on ExDDV, performing experiments with various fine-tuning and in-context learning strategies. Our results show that text and click supervision are both required to develop robust explainable models for deepfake videos, which are able to localize and describe the observed artifacts. Our novel dataset and code to reproduce the results are available at https://github.com/vladhondru25/ExDDV.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 67 of its 88 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

67 of 88 references.

References · 67

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2022Training language models to follow instructions with human feedbackcited by 15,712
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  8. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  9. 2023Visual Instruction Tuningcited by 7,792
  10. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  11. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  12. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
38 more
  1. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  4. 2023Mistral 7Bcited by 3,065
  5. 2015VQA: Visual Question Answeringcited by 2,489
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  7. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  8. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  9. 2023A Comprehensive Overview of Large Language Modelscited by 639
  10. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  11. 2024Large Language Models: A Surveycited by 506
  12. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
  13. 2015Stacked Attention Networks for Image Question Answeringcited by 273
  14. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
  15. 2024EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditionscited by 233
  16. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
  17. 2024Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animationcited by 198
  18. 2024MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidancecited by 196
  19. 2024EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditionscited by 196
  20. 2024VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Timecited by 186
  21. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
  22. 2020Two-branch Recurrent Network for Isolating Deepfakes in Videoscited by 161
  23. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  24. 2023Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generationcited by 142
  25. 2015Exploring Models and Data for Image Question Answeringcited by 139
  26. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  27. 2019Recurrent Convolutional Strategies for Face Manipulation Detection in Videoscited by 118
  28. 2020Learning to Faithfully Rationalize by Constructioncited by 113
  29. 2014A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Inputcited by 112
  30. 2019Large-scale interactive object segmentation with human annotatorscited by 109
  31. 2020ID-Reveal: Identity-aware DeepFake Video Detectioncited by 97
  32. 2024DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmarkcited by 85
  33. 2024V-Express: Conditional Dropout for Progressive Training of Portrait Video Generationcited by 85
  34. 2021Pointly-Supervised Instance Segmentationcited by 83
  35. 2015Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answeringcited by 80
  36. 2023Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Imagescited by 79
  37. 2024AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encodingcited by 67
  38. 2020Detecting Deep-Fake Videos from Appearance and Behaviorcited by 66

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequencescited by 6
  2. 2025GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifactscited by 2
  3. 2025EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoningcited by 2
  4. 2026Explainable Deepfake Detection Challengecited by 2
  5. 2025Investigating self-supervised representations for audio-visual deepfake detectioncited by 1
  6. 2026Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectorscited by 1
  7. 2026Detecting AI-Generated Video: A Vision-Language Dual-View Surveycited by 1
  8. 2025Explainable AI-Generated Image Detection RewardBenchcited by 0
  9. 2026TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videoscited by 0
  10. 2026DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024PUDD: Towards Robust Multi-modal Prototype-based Deepfake Detection
  2. 2023Undercover Deepfakes: Detecting Fake Segments in Videos
  3. 2026MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection
  4. 2026Leveraging large multimodal models for audio-video deepfake detection: a pilot study
  5. 2024The Tug-of-War Between Deepfake Generation and Detection
  6. 2024Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection
  7. 2026Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models
  8. 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges