mlsanityData to 7 Oct 2026

Face X-ray for More General Face Forgery Detection

arXiv 1912.13458 ↗First posted 31 Dec 2019cs.CVcited by 469

Not on the map. Why?

Abstract (arXiv)

In this paper we propose a novel image representation called face X-ray for detecting forgery in face images. The face X-ray of an input face image is a greyscale image that reveals whether the input image can be decomposed into the blending of two images from different sources. It does so by showing the blending boundary for a forged image and the absence of blending for a real image. We observe that most existing face manipulation methods share a common step: blending the altered face into an existing background image. For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms. Face X-ray is general in the sense that it only assumes the existence of a blending step and does not rely on any knowledge of the artifacts associated with a specific face manipulation technique. Indeed, the algorithm for computing face X-ray can be trained without fake images generated by any of the state-of-the-art face manipulation methods. Extensive experiments show that face X-ray remains effective when applied to forgery generated by unseen face manipulation techniques, while most existing face forgery detection or deepfake detection algorithms experience a significant performance drop.

Key facts. Cited by 469 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 63; 2022: 69; 2023: 86; 2024: 92; 2025: 92; 2026: 67.

469 papers.

Sort:

By area:

  1. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  2. 2021Multi-attentional Deepfake Detectioncited by 339
  3. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  4. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  5. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
  6. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  7. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
  8. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
  9. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  10. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  11. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  12. 2023Raising the Cost of Malicious AI-Powered Image Editingcited by 160
38 more
  1. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  2. 2022EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Modelcited by 151
  3. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  4. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  5. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  6. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  7. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  8. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
  9. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  10. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  11. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  12. 2021Local Relation Learning for Face Forgery Detectioncited by 100
  13. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  14. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  15. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  16. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  17. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  18. 2024LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detectioncited by 88
  19. 2021Face Forensics in the Wildcited by 87
  20. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  21. 2023AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Datasetcited by 79
  22. 2023AltFreezing for More General Video Face Forgery Detectioncited by 78
  23. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
  24. 2022UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detectioncited by 69
  25. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 68
  26. 2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
  27. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  28. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanationcited by 66
  29. 2024Common Sense Reasoning for Deepfake Detectioncited by 64
  30. 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detectioncited by 60
  31. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  32. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 58
  33. 2021Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Featurescited by 57
  34. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  35. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  36. 2022MARLIN: Masked Autoencoder for facial video Representation LearnINgcited by 55
  37. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  38. 2021OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildcited by 50

50 most cited of 469 All 469 (JSON)