mlsanityData to 7 Oct 2026

Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos

arXiv 1810.11215 ↗First posted 26 Oct 2018cs.CV eess.IVcited by 180

Not on the map. Why?

Abstract (arXiv)

Recent advances in media generation techniques have made it easier for attackers to create forged images and videos. State-of-the-art methods enable the real-time creation of a forged version of a single video obtained from a social network. Although numerous methods have been developed for detecting forged images and videos, they are generally targeted at certain domains and quickly become obsolete as new kinds of attacks appear. The method introduced in this paper uses a capsule network to detect various kinds of spoofs, from replay attacks using printed images or recorded videos to computer-generated videos using deep convolutional neural networks. It extends the application of capsule networks beyond their original intention to the solving of inverse graphics problems.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 26; 2023: 32; 2024: 31; 2025: 33; 2026: 22.

180 papers.

Sort:

By area:

  1. 2021Multi-attentional Deepfake Detectioncited by 339
  2. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  3. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  4. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  5. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  6. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  7. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  8. 2021Local Relation Learning for Face Forgery Detectioncited by 100
  9. 2023Art and the science of generative AI: A deeper divecited by 93
  10. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  11. 2024LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detectioncited by 88
  12. 2021Deepfake Video Detection Using Convolutional Vision Transformercited by 79
38 more
  1. 2022UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detectioncited by 69
  2. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 68
  3. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  4. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  5. 2021Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Featurescited by 57
  6. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  7. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  8. 2021OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildcited by 50
  9. 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
  10. 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?cited by 48
  11. 2022Voice-Face Homogeneity Tells Deepfakecited by 44
  12. 2021Efficient-CapsNet: Capsule Network with Self-Attention Routingcited by 41
  13. 2023Improving Fairness in Deepfake Detectioncited by 40
  14. 2021Video Transformer for Deepfake Detection with Incremental Learningcited by 33
  15. 2023UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localizationcited by 33
  16. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  17. 2021COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learningcited by 26
  18. 2021TAFIM: Targeted Adversarial Attacks against Facial Image Manipulationscited by 25
  19. 2022Restricted Black-box Adversarial Attack Against DeepFake Face Swappingcited by 25
  20. 2022Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cuescited by 24
  21. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  22. 2023Controllable Guide-Space for Generalizable Face Forgery Detectioncited by 21
  23. 2021DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learningcited by 20
  24. 2023Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localizationcited by 20
  25. 2021TAR: Generalized Forensic Framework to Detect Deepfakes using Weakly Supervised Learningcited by 19
  26. 2025Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensicscited by 18
  27. 2021Conditional Variational Capsule Network for Open Set Recognitioncited by 17
  28. 2022Model Attribution of Face-swap Deepfake Videoscited by 17
  29. 2022Digital and Physical Face Attacks: Reviewing and One Step Furthercited by 17
  30. 2023Detecting Deepfakes Without Seeing Anycited by 17
  31. 2024GM-DF: Generalized Multi-Scenario Deepfake Detectioncited by 16
  32. 2021Detection and Localization of Facial Expression Manipulationscited by 15
  33. 2021Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motioncited by 15
  34. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  35. 2024SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Frameworkcited by 14
  36. 2025From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakescited by 14
  37. 2025FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasingcited by 14
  38. 2023GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformercited by 12

50 most cited of 180 All 180 (JSON)