mlsanityData to 13 Oct 2026

Representative Forgery Mining for Fake Face Detection

arXiv 2104.06609 ↗First posted 14 Apr 2021cs.CVcited by 108

Not on the map. Why?

Abstract (arXiv)

Although vanilla Convolutional Neural Network (CNN) based detectors can achieve satisfactory performance on fake face detection, we observe that the detectors tend to seek forgeries on a limited region of face, which reveals that the detectors is short of understanding of forgery. Therefore, we propose an attention-based data augmentation framework to guide detector refine and enlarge its attention. Specifically, our method tracks and occludes the Top-N sensitive facial regions, encouraging the detector to mine deeper into the regions ignored before for more representative forgery. Especially, our method is simple-to-use and can be easily integrated with various CNN models. Extensive experiments show that the detector trained with our method is capable to separately point out the representative forgery of fake faces generated by different manipulation techniques, and our method enables a vanilla CNN-based detector to achieve state-of-the-art performance without structure modification.

Key facts. Cited by 108 papers in the map (data through 13 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

29 of 38 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,000
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,170
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,585
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,975
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,434
  9. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,326
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,627
  11. 2017Random Erasing Data Augmentationcited by 1,238
  12. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,097
17 more
  1. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  2. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 938
  3. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 846
  4. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  5. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 574
  6. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  7. 2017Fake News Detection on Social Media: A Data Mining Perspectivecited by 335
  8. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  9. 2020What makes fake images detectable? Understanding properties that generalizecited by 273
  10. 2019On the Detection of Digital Face Manipulationcited by 259
  11. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 232
  12. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  13. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  14. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  15. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 118
  16. 2020Do We Need Zero Training Loss After Achieving Zero Training Error?cited by 61
  17. 2020FakeLocator: Robust Localization of GAN-Based Face Manipulationscited by 40

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 2; 2022: 18; 2023: 25; 2024: 26; 2025: 25; 2026: 12.

108 papers.

Sort:

By area:

  1. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  2. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  3. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 163
  4. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  5. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 127
  6. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  7. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 112
  8. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  9. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  10. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
  11. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 58
  12. 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
38 more
  1. 2022Audio-Visual Person-of-Interest DeepFake Detectioncited by 43
  2. 2022Delving into Sequential Patches for Deepfake Detectioncited by 41
  3. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 39
  4. 2022Exploring Disentangled Content Information for Face Forgery Detectioncited by 36
  5. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  6. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  7. 2023DeepFake-Adapter: Dual-Level Adapter for DeepFake Detectioncited by 26
  8. 2021Wavelet-Packets for Deepfake Image Analysis and Detectioncited by 25
  9. 2022MINTIME: Multi-Identity Size-Invariant Video Deepfake Detectioncited by 23
  10. 2023Controllable Guide-Space for Generalizable Face Forgery Detectioncited by 21
  11. 2024Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detectioncited by 21
  12. 2024Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learningcited by 20
  13. 2025Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensicscited by 20
  14. 2022Exposing Deepfake Face Forgeries with Guided Residualscited by 17
  15. 2024GM-DF: Generalized Multi-Scenario Deepfake Detectioncited by 16
  16. 2024SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Frameworkcited by 14
  17. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 13
  18. 2022FedForgery: Generalized Face Forgery Detection with Residual Federated Learningcited by 12
  19. 2024Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensicscited by 12
  20. 2023Multi-spectral Class Center Network for Face Manipulation Detection and Localizationcited by 11
  21. 2024Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detectioncited by 10
  22. 2022Hierarchical Forgery Classifier On Multi-modality Face Forgery Cluescited by 9
  23. 2023Information-containing Adversarial Perturbation for Combating Facial Manipulation Systemscited by 9
  24. 2023Real Face Foundation Representation Learning for Generalized Deepfake Detectioncited by 8
  25. 2024ED4: Explicit Data-level Debiasing for Deepfake Detectioncited by 8
  26. 2025Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detectioncited by 8
  27. 2025RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detectioncited by 8
  28. 2023Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attentioncited by 7
  29. 2023Discrepancy-Guided Reconstruction Learning for Image Forgery Detectioncited by 7
  30. 2025Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakescited by 7
  31. 2025Fair Deepfake Detectors Can Generalizecited by 7
  32. 2023On the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion Modelscited by 6
  33. 2023Self-Supervised Graph Transformer for Deepfake Detectioncited by 6
  34. 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challengescited by 6
  35. 2024ODDN: Addressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networkscited by 6
  36. 2024FakeFormer: Efficient Vulnerability-Driven Transformers for Generalisable Deepfake Detectioncited by 6
  37. 2025Learning Real Facial Concepts for Independent Deepfake Detectioncited by 6
  38. 2025CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillationcited by 6

50 most cited of 108 All 108 (JSON)