mlsanityData to 14 Oct 2026

AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations

arXiv 2507.20579 ↗First posted 28 Jul 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

The rapid surge of text-to-speech and face-voice reenactment models makes video fabrication easier and highly realistic. To encounter this problem, we require datasets that rich in type of generation methods and perturbation strategy which is usually common for online videos. To this end, we propose AV-Deepfake1M++, an extension of the AV-Deepfake1M having 2 million video clips with diversified manipulation strategy and audio-visual perturbation. This paper includes the description of data generation strategies along with benchmarking of AV-Deepfake1M++ using state-of-the-art methods. We believe that this dataset will play a pivotal role in facilitating research in Deepfake domain. Based on this dataset, we host the 2025 1M-Deepfakes Detection Challenge. The challenge details, dataset and evaluation scripts are available online under a research-only license at https://deepfakes1m.github.io/2025.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 28 Jul 2025.

Builds on

33 of 49 references.

References · 33

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  3. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  4. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  5. 2020A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wildcited by 672
  6. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 575
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  8. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  9. 2018LRS3-TED: a large-scale dataset for visual speech recognitioncited by 308
  10. 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 297
  11. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 282
  12. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 254
21 more
  1. 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 209
  2. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 209
  3. 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
  4. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  5. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  6. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
  7. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 108
  8. 2023Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expertcited by 98
  9. 2021Face Forensics in the Wildcited by 87
  10. 2021KoDF: A Large-scale Korean DeepFake Detection Datasetcited by 80
  11. 2023AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Datasetcited by 80
  12. 2024LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervisioncited by 56
  13. 2023Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localizationcited by 43
  14. 2023Do I Have Your Attention: A Large Scale Engagement Prediction Dataset and Baselinescited by 17
  15. 2024Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectorscited by 17
  16. 2024PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Datasetcited by 16
  17. 2023M3Dsynth: A dataset of medical 3D images with AI-generated local manipulationscited by 11
  18. 2025Tell me Habibi, is it Real or Fake?cited by 6
  19. 2025Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulationscited by 5
  20. 20241M-Deepfakes Detection Challengecited by 4
  21. 2025LayLens: Improving Deepfake Understanding through Simplified Explanationscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2026Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalitiescited by 6
  2. 2025Pindrop it! Audio and Visual Deepfake Countermeasures for Robust Detection and Fine Grained-Localizationcited by 3
  3. 2025DGM4+: Dataset Extension for Global Scene Inconsistencycited by 2
  4. 2026Explainable Deepfake Detection Challengecited by 2
  5. 2026Detecting AI-Generated Video: A Vision-Language Dual-View Surveycited by 1
  6. 2025SGS: Segmentation-Guided Scoring for Global Scene Inconsistenciescited by 0
  7. 2026Towards multi-modal forgery representation learning for AI-generated video detection and localizationcited by 0
  8. 2026PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditionscited by 0