mlsanityData to 7 Oct 2026

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

arXiv 1909.04538 ↗First posted 10 Sep 2019cs.CV cs.AI cs.LGcited by 108

Not on the map. Why?

Abstract (arXiv)

We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively on privacy-safe information. Our model is based on a conditional generative adversarial network, generating images considering the original pose and image background. The conditional information enables us to generate highly realistic faces with a seamless transition between the generated face and the existing background. Furthermore, we introduce a diverse dataset of human faces, including unconventional poses, occluded faces, and a vast variability in backgrounds. Finally, we present experimental results reflecting the capability of our model to anonymize images while preserving the data distribution, making the data suitable for further training of deep learning models. As far as we know, no other solution has been proposed that guarantees the anonymization of faces while generating realistic images.

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 14; 2023: 19; 2024: 18; 2025: 19; 2026: 22.

108 papers.

Sort:

By area:

  1. 2022DeepPrivacy2: Towards Realistic Full-Body Anonymizationcited by 51
  2. 2023Attribute-preserving Face Dataset Anonymization via Latent Code Optimizationcited by 43
  3. 2023A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settingscited by 31
  4. 2023Diff-Privacy: Diffusion-based Face Privacy Protectioncited by 25
  5. 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
  6. 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
  7. 2023LDFA: Latent Diffusion Face Anonymization for Self-driving Applicationscited by 21
  8. 2023RiDDLE: Reversible and Diversified De-identification with Latent Encryptorcited by 21
  9. 2021Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semanticscited by 20
  10. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  11. 2024G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priorscited by 20
  12. 2024Face Anonymization Made Simplecited by 18
38 more
  1. 2023MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidancecited by 17
  2. 2021SoK: Anti-Facial Recognition Technologycited by 16
  3. 2021Data synthesis and adversarial networks: A review and meta-analysis in cancer imagingcited by 15
  4. 2022Realistic Full-Body Anonymization with Surface-Guided GANscited by 15
  5. 2022My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymizationcited by 14
  6. 2021CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulationcited by 12
  7. 2023Does Image Anonymization Impact Computer Vision Training?cited by 12
  8. 2023FIVA: Facial Image and Video Anonymization and Anonymization Defensecited by 12
  9. 2022Unsupervised Text Deidentificationcited by 11
  10. 2022StyleID: Identity Disentanglement for Anonymizing Facescited by 10
  11. 2021Graph-based Generative Face Anonymisation with Pose Preservationcited by 9
  12. 2023DisguisOR: Holistic Face Anonymization for the Operating Roomcited by 9
  13. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  14. 2023Disguise without Disruption: Utility-Preserving Face De-Identificationcited by 8
  15. 2021Temporally coherent video anonymization through GAN inpaintingcited by 7
  16. 2024Latent Diffusion Models for Attribute-Preserving Image Anonymizationcited by 7
  17. 2021Exploring the Assessment List for Trustworthy AI in the Context of Advanced Driver-Assistance Systemscited by 6
  18. 2022Learnable Privacy-Preserving Anonymization for Pedestrian Imagescited by 6
  19. 2021DeepFN: Towards Generalizable Facial Action Unit Recognition with Deep Face Normalizationcited by 5
  20. 2021Anonymization for Skeleton Action Recognitioncited by 5
  21. 2022MaSS: Multi-attribute Selective Suppressioncited by 5
  22. 2023Anonymizing medical case-based explanations through disentanglementcited by 5
  23. 2025Evaluation of Human Visual Privacy Protection: A Three-Dimensional Framework and Benchmark Datasetcited by 5
  24. 2022Fantomas: Understanding Face Anonymization Reversibilitycited by 4
  25. 2024Privacy-preserving Optics for Enhancing Protection in Face De-identificationcited by 4
  26. 2024Medical Manifestation-Aware De-Identificationcited by 4
  27. 2025NullFace: Training-Free Localized Face Anonymizationcited by 4
  28. 2025Bi-Level Optimization for Self-Supervised AI-Generated Face Detectioncited by 4
  29. 2021Safe Fakes: Evaluating Face Anonymizers for Face Detectorscited by 3
  30. 2024MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspectivecited by 3
  31. 2025Self-Supervised Learning for Detecting AI-Generated Faces as Anomaliescited by 3
  32. 2021Conditional De-Identification of 3D Magnetic Resonance Imagescited by 2
  33. 2022GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservationcited by 2
  34. 2022StyleGAN as a Utility-Preserving Face De-identification Methodcited by 2
  35. 2024Exploring AI-based Anonymization of Industrial Image and Video Data in the Context of Feature Preservationcited by 2
  36. 2024Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approachcited by 2
  37. 2024Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognitioncited by 2
  38. 2025BLANKET: Anonymizing Faces in Infant Video Recordingscited by 2

50 most cited of 108 All 108 (JSON)