mlsanityData to 7 Oct 2026

Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review

arXiv 2208.10913 ↗First posted 21 Aug 2022cs.CV cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent advancements in AI, especially deep learning, have contributed to a significant increase in the creation of new realistic-looking synthetic media (video, image, and audio) and manipulation of existing media, which has led to the creation of the new term ``deepfake''. Based on both the research literature and resources in English and in Chinese, this paper gives a comprehensive overview of deepfake, covering multiple important aspects of this emerging concept, including 1) different definitions, 2) commonly used performance metrics and standards, and 3) deepfake-related datasets, challenges, competitions and benchmarks. In addition, the paper also reports a meta-review of 12 selected deepfake-related survey papers published in 2020 and 2021, focusing not only on the mentioned aspects, but also on the analysis of key challenges and recommendations. We believe that this paper is the most comprehensive review of deepfake in terms of aspects covered, and the first one covering both the English and Chinese literature and sources.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 67 of its 143 references that are in the map. First posted on arXiv 21 Aug 2022.

Builds on

67 of 143 references.

References · 67

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  5. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  8. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  9. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  10. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  11. 2022Expanding Language-Image Pretrained Models for General Video Recognitioncited by 320
  12. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
38 more
  1. 2018Deep Video Portraitscited by 265
  2. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  3. 2019On the Detection of Digital Face Manipulationcited by 259
  4. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
  5. 2020The Creation and Detection of Deepfakes: A Surveycited by 246
  6. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 231
  7. 2019FaceShifter: Towards High Fidelity And Occlusion Aware Face Swappingcited by 221
  8. 2018Efficient Neural Audio Synthesiscited by 218
  9. 2020Media Forensics and DeepFakes: an overviewcited by 208
  10. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
  11. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 173
  12. 2020Adversarial Latent Autoencoderscited by 155
  13. 2019FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signalscited by 143
  14. 2020DeepFaceLab: Integrated, flexible and extensible face-swapping frameworkcited by 129
  15. 2022Does Audio Deepfake Detection Generalize?cited by 129
  16. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 126
  17. 2018Two-Stream Neural Networks for Tampered Face Detectioncited by 125
  18. 2020The DeepFake Detection Challenge (DFDC) Datasetcited by 125
  19. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
  20. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 118
  21. 2021TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generationcited by 118
  22. 2020TweepFake: about Detecting Deepfake Tweetscited by 117
  23. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  24. 2019Deep Learning for Deepfakes Creation and Detection: A Surveycited by 102
  25. 2018Neural Voice Cloning with a Few Samplescited by 100
  26. 2022BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotationscited by 99
  27. 2022ADD 2022: the First Audio Deep Synthesis Detection Challengecited by 94
  28. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  29. 2018Recycle-GAN: Unsupervised Video Retargetingcited by 89
  30. 2021Face Forensics in the Wildcited by 87
  31. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  32. 2021KoDF: A Large-scale Korean DeepFake Detection Datasetcited by 80
  33. 2019Unmasking DeepFakes with simple Featurescited by 78
  34. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  35. 2020Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversioncited by 75
  36. 2018The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodscited by 68
  37. 2019Neural Style-Preserving Visual Dubbingcited by 47
  38. 2020DeepFake Detection: Current Challenges and Next Stepscited by 44

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.

  1. 2024Distinguish Any Fake Videos: Unleashing the Power of Large-scale Data and Motion Featurescited by 20
  2. 2025DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detectioncited by 3
  3. 2026The Deepfakes We Missed: We Built Detectors for a Threat That Didn't Arrivecited by 0
  4. 2026Ensemble Deep Learning Approaches for AI-Altered Video Detectioncited by 0
  5. 2026A Dual-Stream Challenge-Response Protocol for Ocular Liveness Verificationcited by 0
  6. 2026Deepfakes and Synthetic Media: Generation, Detection, and Governancecited by 0