mlsanityData to 7 Oct 2026

UCF: Uncovering Common Features for Generalizable Deepfake Detection

arXiv 2304.13949 ↗First posted 27 Apr 2023cs.CVcited by 177

Not on the map. Why?

Abstract (arXiv)

Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detection methods to forgery-irrelevant features and method-specific patterns. The latter has been rarely studied and not well addressed by previous works. This paper presents a novel approach to address the two types of overfitting issues by uncovering common forgery features. Specifically, we first propose a disentanglement framework that decomposes image information into three distinct components: forgery-irrelevant, method-specific forgery, and common forgery features. To ensure the decoupling of method-specific and common forgery features, a multi-task learning strategy is employed, including a multi-class classification that predicts the category of the forgery method and a binary classification that distinguishes the real from the fake. Additionally, a conditional decoder is designed to utilize forgery features as a condition along with forgery-irrelevant features to generate reconstructed images. Furthermore, a contrastive regularization technique is proposed to encourage the disentanglement of the common and specific forgery features. Ultimately, we only utilize the common forgery features for the purpose of generalizable deepfake detection. Extensive evaluations demonstrate that our framework can perform superior generalization than current state-of-the-art methods.

Key facts. Cited by 177 papers in the map (data through 7 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

44 of 63 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  7. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  8. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  9. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  10. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  11. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  12. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
32 more
  1. 2021Multi-attentional Deepfake Detectioncited by 339
  2. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  3. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  4. 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 294
  5. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
  6. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  7. 2019On the Detection of Digital Face Manipulationcited by 259
  8. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  9. 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
  10. 2020Learning Self-Consistency for Deepfake Detectioncited by 179
  11. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  12. 2020Two-branch Recurrent Network for Isolating Deepfakes in Videoscited by 161
  13. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  14. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  15. 2019Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videoscited by 130
  16. 2018Two-Stream Neural Networks for Tampered Face Detectioncited by 125
  17. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
  18. 2019Recurrent Convolutional Strategies for Face Manipulation Detection in Videoscited by 118
  19. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  20. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  21. 2021Local Relation Learning for Face Forgery Detectioncited by 100
  22. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
  23. 2020Face Anti-Spoofing Via Disentangled Representation Learningcited by 65
  24. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  25. 2021Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Featurescited by 57
  26. 2020Sharp Multiple Instance Learning for DeepFake Video Detectioncited by 54
  27. 2020Face Forgery Detection by 3D Decompositioncited by 53
  28. 2022Exploring Disentangled Content Information for Face Forgery Detectioncited by 36
  29. 2021Towards Solving the DeepFake Problem : An Analysis on Improving DeepFake Detection using Dynamic Face Augmentationcited by 25
  30. 2021Learning to Disentangle GAN Fingerprint for Fake Image Attributioncited by 19
  31. 2021Finding Facial Forgery Artifacts with Parts-Based Detectorscited by 14
  32. 2022Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection using Adversarial Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 52; 2025: 60; 2026: 55.

177 papers.

Sort:

By area:

  1. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  2. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 155
  3. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  4. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  5. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 111
  6. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  7. 2024LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detectioncited by 88
  8. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  9. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 58
  10. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  11. 2024FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledgecited by 48
  12. 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?cited by 48
38 more
  1. 2023Towards General Visual-Linguistic Face Forgery Detectioncited by 45
  2. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 38
  3. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  4. 2024OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarkingcited by 35
  5. 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detectioncited by 34
  6. 2024Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detectioncited by 30
  7. 2024Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detectioncited by 30
  8. 2024DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusioncited by 29
  9. 2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
  10. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  11. 2024Detecting AI-Generated Video via Frame Consistencycited by 26
  12. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  13. 2024FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learningcited by 21
  14. 2025Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detectioncited by 20
  15. 2024Generative Unlearning for Any Identitycited by 19
  16. 2025Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensicscited by 18
  17. 2023Detecting Deepfakes Without Seeing Anycited by 17
  18. 2024GM-DF: Generalized Multi-Scenario Deepfake Detectioncited by 16
  19. 2024Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detectioncited by 16
  20. 2025SketchVideo: Sketch-based Video Generation and Editingcited by 15
  21. 2025From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakescited by 14
  22. 2025FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasingcited by 14
  23. 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
  24. 202550 Years of Automated Face Recognitioncited by 13
  25. 2026Your One-Stop Solution for AI-Generated Video Detectioncited by 13
  26. 2024Robustly Optimized Deep Feature Decoupling Network for Fatty Liver Diseases Detectioncited by 11
  27. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  28. 2025Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detectioncited by 10
  29. 2024Diffusion Deepfakecited by 8
  30. 2024Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Methodcited by 8
  31. 2024Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluationscited by 8
  32. 2024ED4: Explicit Data-level Debiasing for Deepfake Detectioncited by 8
  33. 2024Wavelet-Driven Generalizable Framework for Deepfake Face Forgery Detectioncited by 8
  34. 2025Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detectioncited by 8
  35. 2024Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixturecited by 7
  36. 2025Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakescited by 7
  37. 2025Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generationcited by 7
  38. 2025Fair Deepfake Detectors Can Generalizecited by 7

50 most cited of 177 All 177 (JSON)