mlsanityData to 7 Oct 2026

Exploiting Style Latent Flows for Generalizing Deepfake Video Detection

arXiv 2403.06592 ↗First posted 11 Mar 2024cs.CV cs.AIcited by 58

Not on the map. Why?

Abstract (arXiv)

This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos. We discovered that the generated facial videos suffer from the temporal distinctiveness in the temporal changes of style latent vectors, which are inevitable during the generation of temporally stable videos with various facial expressions and geometric transformations. Our framework utilizes the StyleGRU module, trained by contrastive learning, to represent the dynamic properties of style latent vectors. Additionally, we introduce a style attention module that integrates StyleGRU-generated features with content-based features, enabling the detection of visual and temporal artifacts. We demonstrate our approach across various benchmark scenarios in deepfake detection, showing its superiority in cross-dataset and cross-manipulation scenarios. Through further analysis, we also validate the importance of using temporal changes of style latent vectors to improve the generality of deepfake video detection.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

49 of 64 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  8. 2020Supervised Contrastive Learningcited by 2,803
  9. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  10. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  11. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  12. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
37 more
  1. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  2. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  3. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  4. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  5. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  6. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  7. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  8. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  9. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  10. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  11. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
  12. 2020What makes fake images detectable? Understanding properties that generalizecited by 272
  13. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 267
  14. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
  15. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  16. 2019FaceShifter: Towards High Fidelity And Occlusion Aware Face Swappingcited by 221
  17. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  18. 2018Do GANs leave artificial fingerprints?cited by 188
  19. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  20. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  21. 2020Two-branch Recurrent Network for Isolating Deepfakes in Videoscited by 161
  22. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  23. 2019Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videoscited by 130
  24. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  25. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
  26. 2019Recurrent Convolutional Strategies for Face Manipulation Detection in Videoscited by 118
  27. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  28. 2021One Shot Face Swapping on Megapixelscited by 105
  29. 2021Local Relation Learning for Face Forgery Detectioncited by 100
  30. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  31. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  32. 2023AltFreezing for More General Video Face Forgery Detectioncited by 78
  33. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  34. 2022Fine-Grained Face Swapping via Regional GAN Inversioncited by 67
  35. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  36. 2022High-resolution Face Swapping via Latent Semantics Disentanglementcited by 57
  37. 2022Region-Aware Face Swappingcited by 45

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 31; 2026: 13.

58 papers.

Sort:

By area:

  1. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  2. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  3. 2024Diffusion Model-Based Video Editing: A Surveycited by 44
  4. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 40
  5. 2024Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Modelcited by 37
  6. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  7. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  8. 2024Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Contentcited by 22
  9. 2024FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learningcited by 21
  10. 2025Deepfake Detection that Generalizes Across Benchmarkscited by 20
  11. 2025From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakescited by 14
  12. 2025FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasingcited by 14
38 more
  1. 2025Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detectioncited by 12
  2. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  3. 2025ExDDV: A New Dataset for Explainable Deepfake Detection in Videocited by 10
  4. 2025Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detectioncited by 10
  5. 2025TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detectioncited by 10
  6. 2025MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmarkcited by 9
  7. 2024Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Methodcited by 8
  8. 2024FaceShield: Defending Facial Image against Deepfake Threatscited by 8
  9. 2025Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detectioncited by 8
  10. 2025Beyond Face Swapping: A Diffusion-Based Digital Human Benchmark for Multimodal Deepfake Detectioncited by 7
  11. 2025Fair Deepfake Detectors Can Generalizecited by 7
  12. 2025DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysiscited by 7
  13. 2025Learning Real Facial Concepts for Independent Deepfake Detectioncited by 6
  14. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  15. 2026Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervisioncited by 5
  16. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  17. 2025Rethinking Individual Fairness in Deepfake Detectioncited by 4
  18. 2025SEED: A Benchmark Dataset for Sequential Facial Attribute Editing with Diffusion Modelscited by 3
  19. 2025AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localizationcited by 3
  20. 2025Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detectioncited by 2
  21. 2025Robust and Calibrated Detection of Authentic Multimedia Contentcited by 2
  22. 2026CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detectioncited by 2
  23. 2024Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detectioncited by 1
  24. 2025RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignmentcited by 1
  25. 2025SELFI: Selective Fusion of Identity for Generalizable Deepfake Detectioncited by 1
  26. 2025Grab-3D: Detecting AI-Generated Videos from 3D Geometric Temporal Consistencycited by 1
  27. 2025FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videoscited by 1
  28. 2026Safeguarding Facial Identity against Diffusion-based Face Swapping via Cascading Pathway Disruptioncited by 1
  29. 2026Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detectioncited by 1
  30. 2024Multiple Contexts and Frequencies Aggregation Network forDeepfake Detectioncited by 0
  31. 2024Revisiting Face Forgery Detection: From Facial Representation to Forgery Detectioncited by 0
  32. 2025Towards General Visual-Linguistic Face Forgery Detection(V2)cited by 0
  33. 2025Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attackscited by 0
  34. 2025CAST: Cross-Attentive Spatio-Temporal feature fusion for deepfake detectioncited by 0
  35. 2025Suppressing Gradient Conflict for Generalizable Deepfake Detectioncited by 0
  36. 2025R2M: Real-Aware Residual Model Merging for Robust and Generalizable Deepfake Detectioncited by 0
  37. 2025Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagerycited by 0
  38. 2026Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detectioncited by 0

50 most cited of 58 All 58 (JSON)