mlsanityData to 14 Oct 2026

Beyond Deepfake Images: Detecting AI-Generated Videos

arXiv 2404.15955 ↗First posted 24 Apr 2024cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic image detectors are unable to detect synthetic videos. We demonstrate that this is because synthetic video generators introduce substantially different traces than those left by image generators. Despite this, we show that synthetic video traces can be learned, and used to perform reliable synthetic video detection or generator source attribution even after H.264 re-compression. Furthermore, we demonstrate that while detecting videos from new generators through zero-shot transferability is challenging, accurate detection of videos from a new generator can be achieved through few-shot learning.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 55 of its 96 references that are in the map. First posted on arXiv 24 Apr 2024.

Builds on

55 of 96 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2016Densely Connected Convolutional Networkscited by 6,720
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  12. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
38 more
  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  4. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  6. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  7. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  8. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  9. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  10. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  11. 2018Image Transformercited by 772
  12. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 658
  13. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  14. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 579
  15. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 546
  16. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 535
  17. 2022MAGVIT: Masked Generative Video Transformercited by 346
  18. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  19. 2022On the detection of synthetic images generated by diffusion modelscited by 283
  20. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  21. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 197
  22. 2018Do GANs leave artificial fingerprints?cited by 190
  23. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  24. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  25. 2020Latent Video Transformercited by 106
  26. 2023DiffiT: Diffusion Vision Transformers for Image Generationcited by 106
  27. 20233D-aware Image Generation using 2D Diffusion Modelscited by 69
  28. 2023Conditional Text Image Generation with Diffusion Modelscited by 58
  29. 2021Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptionscited by 53
  30. 2023Text2Performer: Text-Driven Human Video Generationcited by 53
  31. 2022Temporally Consistent Transformers for Video Generationcited by 44
  32. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  33. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 44
  34. 2024Diffusion Facial Forgery Detectioncited by 41
  35. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  36. 2023GenDet: Towards Good Generalizations for AI-Generated Image Detectioncited by 36
  37. 2020Detecting CNN-Generated Facial Images in Real-World Scenarioscited by 32
  38. 2023Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysiscited by 30

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 8; 2026: 9.

22 papers.

Sort:

By area:

  1. 2024Taming Data and Transformers for Audio Generationcited by 28
  2. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  3. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  4. 2025DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoningcited by 9
  5. 2025TrueFake: A Real World Case Dataset of Last Generation Fake Images also Shared on Social Networkscited by 8
  6. 2026Training-free Detection of Generated Videos via Spatial-Temporal Likelihoodscited by 8
  7. 2024When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Launderingcited by 7
  8. 2024Improving Interpretability and Robustness for the Detection of AI-Generated Imagescited by 5
  9. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  10. 2024Human Action CLIPs: Detecting AI-generated Human Motioncited by 4
  11. 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencingcited by 2
  12. 2025SAGA: Source Attribution of Generative AI Videoscited by 2
10 more
  1. 2026CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detectioncited by 2
  2. 2025A Practical Synthesis of Detecting AI-Generated Textual, Visual, and Audio Contentcited by 1
  3. 2025Autonomous and Self-Adapting System for Synthetic Media Detection and Attributioncited by 1
  4. 2026GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?cited by 1
  5. 2026Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detectioncited by 1
  6. 2026Detecting AI-Generated Video: A Vision-Language Dual-View Surveycited by 1
  7. 2026SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detectioncited by 1
  8. 2026Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challengecited by 0
  9. 2026Retrieval-Driven Training-Free AI-Generated Video Attributioncited by 0
  10. 2026TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videoscited by 0