mlsanityData to 14 Oct 2026

MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark

arXiv 2505.11109 ↗First posted 16 May 2025cs.CV cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We present the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Our dataset comprises over 250 hours of real and fake videos across eight languages, with 60% of data being generated. For each language, the fake videos are generated with seven distinct deepfake generation models, selected based on the quality of the generated content. We organize the training, validation and test splits such that only a subset of the chosen generative models and languages are available during training, thus creating several challenging open-set evaluation setups. We perform experiments with various pre-trained and fine-tuned deepfake detectors proposed in recent literature. Our results show that state-of-the-art detectors are not currently able to maintain their performance levels when tested in our open-set scenarios. We publicly release our data and code at: https://huggingface.co/datasets/unibuc-cs/MAVOS-DD.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 56 of its 77 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

56 of 77 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  12. 2022Diffusion Models in Vision: A Surveycited by 1,015
38 more
  1. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  2. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 575
  3. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 349
  4. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 320
  5. 2019On the Detection of Digital Face Manipulationcited by 260
  6. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 254
  7. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  8. 2024EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditionscited by 235
  9. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  10. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  11. 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 209
  12. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 209
  13. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 206
  14. 2024Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animationcited by 202
  15. 2024EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditionscited by 196
  16. 2024VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Timecited by 187
  17. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  18. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 159
  19. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  20. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
  21. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 121
  22. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  23. 2021Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detectioncited by 113
  24. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  25. 2021HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swappingcited by 92
  26. 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 82
  27. 2024Sonic: Shifting Focus to Global Audio Perception in Portrait Animationcited by 72
  28. 2020Video Face Manipulation Detection Through Ensemble of CNNscited by 63
  29. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 59
  30. 2024AVFF: Audio-Visual Feature Fusion for Video Deepfake Detectioncited by 59
  31. 2024Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detectioncited by 47
  32. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 45
  33. 2022Audio-Visual Person-of-Interest DeepFake Detectioncited by 43
  34. 2022Delving into Sequential Patches for Deepfake Detectioncited by 41
  35. 2024MEMO: Memory-Guided Diffusion for Expressive Talking Video Generationcited by 38
  36. 2024DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysiscited by 30
  37. 2024Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networkscited by 27
  38. 2024Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detectioncited by 24

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2025Fit for Purpose? Deepfake Detection in the Real Worldcited by 4
  2. 2026Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detectioncited by 3
  3. 2026Detecting AI-Generated Video: A Vision-Language Dual-View Surveycited by 1
  4. 2026Leveraging large multimodal models for audio-video deepfake detection: a pilot studycited by 0
  5. 2026Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakescited by 0
  6. 2026Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challengecited by 0
  7. 2026Foundation Models are Implicit Deepfake Detectorscited by 0
  8. 2026DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Expertscited by 0
  9. 2026DF26: We Cannot Tell Fake From Real Anymorecited by 0