mlsanityData to 7 Oct 2026

Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos

arXiv 2305.03713 ↗First posted 5 May 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Modern avatar generators allow anyone to synthesize photorealistic real-time talking avatars, ushering in a new era of avatar-based human communication, such as with immersive AR/VR interactions or videoconferencing with limited bandwidths. Their safe adoption, however, requires a mechanism to verify if the rendered avatar is trustworthy: does it use the appearance of an individual without their consent? We term this task avatar fingerprinting. To tackle it, we first introduce a large-scale dataset of real and synthetic videos of people interacting on a video call, where the synthetic videos are generated using the facial appearance of one person and the expressions of another. We verify the identity driving the expressions in a synthetic video, by learning motion signatures that are independent of the facial appearance shown. Our solution, the first in this space, achieves an average AUC of 0.85. Critical to its practical use, it also generalizes to new generators never seen in training (average AUC of 0.83). The proposed dataset and other resources can be found at: https://research.nvidia.com/labs/nxp/avatar-fingerprinting/.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 46 of its 114 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

46 of 114 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  6. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  7. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  8. 2020First Order Motion Model for Image Animationcited by 698
  9. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
  10. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  11. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  12. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
34 more
  1. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  2. 2018Deep Video Portraitscited by 265
  3. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  4. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
  5. 2022Thin-Plate Spline Motion Model for Image Animationcited by 209
  6. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  7. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 177
  8. 2022Latent Image Animator: Learning to Animate Images via Latent Space Navigationcited by 172
  9. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  10. 2022MegaPortraits: One-shot Megapixel Neural Head Avatarscited by 131
  11. 2020The DeepFake Detection Challenge (DFDC) Datasetcited by 125
  12. 2021Pixel Codec Avatarscited by 125
  13. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
  14. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  15. 2020Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatarscited by 116
  16. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  17. 2020Lipreading using Temporal Convolutional Networkscited by 98
  18. 2020ID-Reveal: Identity-aware DeepFake Video Detectioncited by 97
  19. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  20. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 90
  21. 2020Distortion Agnostic Deep Watermarkingcited by 88
  22. 2021KoDF: A Large-scale Korean DeepFake Detection Datasetcited by 80
  23. 2020Detecting Deep-Fake Videos from Appearance and Behaviorcited by 66
  24. 2022Drivable Volumetric Avatars using Texel-Aligned Featurescited by 62
  25. 2019Neural Style-Preserving Visual Dubbingcited by 47
  26. 2022Implicit Warping for Animation with Image Setscited by 45
  27. 2022Audio-Visual Person-of-Interest DeepFake Detectioncited by 43
  28. 2017Improving Landmark Localization with Semi-Supervised Learningcited by 39
  29. 2019Source Generator Attribution via Inversioncited by 21
  30. 2021Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motioncited by 15
  31. 2022A Review of Deep Learning-based Approaches for Deepfake Content Detectioncited by 12
  32. 2020VideoForensicsHQ: Detecting High-quality Manipulated Face Videoscited by 8
  33. 2021DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Resultscited by 6
  34. 2022Study of detecting behavioral signatures within DeepFake videoscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 4.

11 papers.

  1. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  2. 2024What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANscited by 12
  3. 2024Is JPEG AI going to change image forensics?cited by 4
  4. 2025Is It Really You? Exploring Biometric Verification Scenarios in Photorealistic Talking-Head Avatar Videoscited by 3
  5. 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencingcited by 2
  6. 2026Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmarkcited by 2
  7. 2024Securing Social Media Against Deepfakes using Identity, Behavioral, and Geometric Signaturescited by 1
  8. 2026ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptationcited by 1
  9. 2025Instant Expressive Gaussian Head Avatars at Over 100 FPScited by 0
  10. 2026Micro-Expression-Aware Avatar Fingerprinting via Inter-Frame Feature Differencingcited by 0
  11. 2026FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Imagecited by 0