mlsanityData to 7 Oct 2026

My Face My Choice: Privacy Enhancing Deepfakes for Social Media Anonymization

arXiv 2211.01361 ↗First posted 2 Nov 2022cs.CV cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

Recently, productization of face recognition and identification algorithms have become the most controversial topic about ethical AI. As new policies around digital identities are formed, we introduce three face access models in a hypothetical social network, where the user has the power to only appear in photos they approve. Our approach eclipses current tagging systems and replaces unapproved faces with quantitatively dissimilar deepfakes. In addition, we propose new metrics specific for this task, where the deepfake is generated at random with a guaranteed dissimilarity. We explain access models based on strictness of the data flow, and discuss impact of each model on privacy, usability, and performance. We evaluate our system on Facial Descriptor Dataset as the real dataset, and two synthetic datasets with random and equal class distributions. Running seven SOTA face recognizers on our results, MFMC reduces the average accuracy by 61%. Lastly, we extensively analyze similarity metrics, deepfake generators, and datasets in structural, visual, and generative spaces; supporting the design choices and verifying the quality.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 34 of its 72 references that are in the map. First posted on arXiv 2 Nov 2022.

Builds on

34 of 72 references.

References · 34

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  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. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2018Datasheets for Datasetscited by 1,371
  6. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  7. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  8. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  9. 2016A Learned Representation For Artistic Stylecited by 340
  10. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  11. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
  12. 2018Additive Margin Softmax for Face Verificationcited by 275
22 more
  1. 2018Deep Face Recognition: A Surveycited by 275
  2. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  3. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  4. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  5. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  6. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  7. 2016Fast Face-swap Using Convolutional Neural Networkscited by 119
  8. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  9. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  10. 2020CIAGAN: Conditional Identity Anonymization Generative Adversarial Networkscited by 88
  11. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 79
  12. 2017On Face Segmentation, Face Swapping, and Face Perceptioncited by 71
  13. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  14. 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
  15. 2019Live Face De-Identification in Videocited by 48
  16. 2018A Hybrid Model for Identity Obfuscation by Face Replacementcited by 43
  17. 2017Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspectivecited by 38
  18. 2016Faceless Person Recognition; Privacy Implications in Social Mediacited by 27
  19. 2021IdentityDP: Differential Private Identification Protection for Face Imagescited by 24
  20. 2020The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footagecited by 16
  21. 2015Facial Descriptors for Human Interaction Recognition In Still Imagescited by 7
  22. 2021MixSyn: Learning Composition and Style for Multi-Source Image Synthesiscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 4; 2026: 2.

14 papers.

Sort:

By area:

  1. 2023DataDAM: Efficient Dataset Distillation with Attention Matchingcited by 83
  2. 2024Face Anonymization Made Simplecited by 18
  3. 2025CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulationcited by 16
  4. 2023Does Image Anonymization Impact Computer Vision Training?cited by 12
  5. 2023FIVA: Facial Image and Video Anonymization and Anonymization Defensecited by 12
  6. 2023My Art My Choice: Adversarial Protection Against Unruly AIcited by 5
  7. 2025NullFace: Training-Free Localized Face Anonymizationcited by 4
  8. 2024My Body My Choice: Human-Centric Full-Body Anonymizationcited by 2
  9. 2025Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymizationcited by 1
  10. 2024Enhanced Facial Feature Extraction and Recignation Using Optimal Fully Dispersed Haar-like Filterscited by 0
  11. 2024Forbes: Face Obfuscation Rendering via Backpropagation Refinement Schemecited by 0
  12. 2025PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymizationcited by 0
2 more
  1. 2026HYDRO: Towards Non-Reversible Face De-Identification Using a High-Fidelity Hybrid Diffusion and Target-Oriented Approachcited by 0
  2. 2026Adversarial Attacks and Identity Leakage in De-Identification Systems: An Empirical Studycited by 0