mlsanityData to 7 Oct 2026

Multi-attentional Deepfake Detection

arXiv 2103.02406 ↗First posted 3 Mar 2021cs.CVcited by 339

Not on the map. Why?

Abstract (arXiv)

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research topic and many deepfake detection methods have been proposed. Most of them model deepfake detection as a vanilla binary classification problem, i.e, first use a backbone network to extract a global feature and then feed it into a binary classifier (real/fake). But since the difference between the real and fake images in this task is often subtle and local, we argue this vanilla solution is not optimal. In this paper, we instead formulate deepfake detection as a fine-grained classification problem and propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps. Moreover, to address the learning difficulty of this network, we further introduce a new regional independence loss and an attention guided data augmentation strategy. Through extensive experiments on different datasets, we demonstrate the superiority of our method over the vanilla binary classifier counterparts, and achieve state-of-the-art performance.

Key facts. Cited by 339 papers in the map (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

35 of 53 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  6. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  7. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  8. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  9. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  10. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  11. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  12. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
23 more
  1. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  2. 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 294
  3. 2018Additive Margin Softmax for Face Verificationcited by 275
  4. 2019On the Detection of Digital Face Manipulationcited by 259
  5. 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
  6. 2019RetinaFace: Single-stage Dense Face Localisation in the Wildcited by 164
  7. 2020Two-branch Recurrent Network for Isolating Deepfakes in Videoscited by 161
  8. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  9. 2019FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signalscited by 143
  10. 2019Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videoscited by 130
  11. 2018Two-Stream Neural Networks for Tampered Face Detectioncited by 125
  12. 2020The DeepFake Detection Challenge (DFDC) Datasetcited by 125
  13. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 107
  14. 2018Learning to Navigate for Fine-grained Classificationcited by 103
  15. 2020Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patchescited by 92
  16. 2018ReenactGAN: Learning to Reenact Faces via Boundary Transfercited by 85
  17. 2017Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detectioncited by 56
  18. 2019See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classificationcited by 56
  19. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  20. 2018RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spacescited by 50
  21. 2020Head2Head: Video-based Neural Head Synthesiscited by 40
  22. 2015Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networkscited by 22
  23. 2019FReeNet: Multi-Identity Face Reenactmentcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 67; 2023: 83; 2024: 69; 2025: 66; 2026: 36.

339 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  3. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  4. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  5. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  6. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  7. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  8. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  9. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
  10. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  11. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  12. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
38 more
  1. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  2. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  3. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  4. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  5. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  6. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  7. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
  8. 2023Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesiscited by 72
  9. 2022UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detectioncited by 69
  10. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  11. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  12. 2024FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistantcited by 59
  13. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  14. 2021CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakescited by 54
  15. 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
  16. 2022Deepfake Detection: A Comprehensive Survey from the Reliability Perspectivecited by 48
  17. 2022Deepfake Network Architecture Attributioncited by 47
  18. 2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
  19. 2023Towards General Visual-Linguistic Face Forgery Detectioncited by 45
  20. 2022Voice-Face Homogeneity Tells Deepfakecited by 44
  21. 2022Audio-Visual Person-of-Interest DeepFake Detectioncited by 43
  22. 2023Perceptual Artifacts Localization for Image Synthesis Taskscited by 43
  23. 2022Delving into Sequential Patches for Deepfake Detectioncited by 41
  24. 2023Improving Fairness in Deepfake Detectioncited by 40
  25. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  26. 2021Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltalescited by 39
  27. 2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
  28. 2024SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Modelscited by 39
  29. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  30. 2022Exploring Disentangled Content Information for Face Forgery Detectioncited by 36
  31. 2022Learning Second Order Local Anomaly for General Face Forgery Detectioncited by 36
  32. 2023Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Modelscited by 36
  33. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  34. 2022On Improving Cross-dataset Generalization of Deepfake Detectorscited by 34
  35. 2022Detecting and Recovering Sequential DeepFake Manipulationcited by 34
  36. 2022Explaining Deepfake Detection by Analysing Image Matchingcited by 34
  37. 2024Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detectioncited by 34
  38. 2023UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localizationcited by 33

50 most cited of 339 All 339 (JSON)