mlsanityData to 7 Oct 2026

Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics

arXiv 2104.01753 ↗First posted 5 Apr 2021cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

With the growing use of camera devices, the industry has many image datasets that provide more opportunities for collaboration between the machine learning community and industry. However, the sensitive information in the datasets discourages data owners from releasing these datasets. Despite recent research devoted to removing sensitive information from images, they provide neither meaningful privacy-utility trade-off nor provable privacy guarantees. In this study, with the consideration of the perceptual similarity, we propose perceptual indistinguishability (PI) as a formal privacy notion particularly for images. We also propose PI-Net, a privacy-preserving mechanism that achieves image obfuscation with PI guarantee. Our study shows that PI-Net achieves significantly better privacy utility trade-off through public image data.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 5 Apr 2021.

Builds on

32 of 53 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  8. 2017Improved Training of Wasserstein GANscited by 2,223
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  12. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
20 more
  1. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  2. 2017Renyi Differential Privacycited by 643
  3. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  4. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  5. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 231
  6. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  7. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  8. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  9. 2019DeepPrivacy: A Generative Adversarial Network for Face Anonymizationcited by 108
  10. 2020CIAGAN: Conditional Identity Anonymization Generative Adversarial Networkscited by 88
  11. 2017Generative Face Completioncited by 79
  12. 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
  13. 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
  14. 2019RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributescited by 56
  15. 2019AnonymousNet: Natural Face De-Identification with Measurable Privacycited by 50
  16. 2019Live Face De-Identification in Videocited by 48
  17. 2019Adversarial Learning of Privacy-Preserving and Task-Oriented Representationscited by 35
  18. 2019Make a Face: Towards Arbitrary High Fidelity Face Manipulationcited by 29
  19. 2016Faceless Person Recognition; Privacy Implications in Social Mediacited by 27
  20. 2017A Domain Based Approach to Social Relation Recognitioncited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 7; 2024: 4; 2025: 3; 2026: 1.

20 papers.

Sort:

  1. 2023CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Searchcited by 42
  2. 2024G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priorscited by 20
  3. 2022GAN-based Facial Attribute Manipulationcited by 16
  4. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  5. 2023Disguise without Disruption: Utility-Preserving Face De-Identificationcited by 8
  6. 2022Learnable Privacy-Preserving Anonymization for Pedestrian Imagescited by 6
  7. 2021Task-aware Privacy Preservation for Multi-dimensional Datacited by 5
  8. 2022MaSS: Multi-attribute Selective Suppressioncited by 5
  9. 2023On Mask-based Image Set Desensitization with Recognition Supportcited by 2
  10. 2024Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Modelscited by 2
  11. 2023Seeing is not Believing: An Identity Hider for Human Vision Privacy Protectioncited by 1
  12. 2024SemDP: Semantic-level Differential Privacy Protection for Face Datasetscited by 1
8 more
  1. 2025ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restorationcited by 1
  2. 2022Contextualize differential privacy in image database: a lightweight image differential privacy approach based on principle component analysis inversecited by 0
  3. 2023Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesiscited by 0
  4. 2023Privacy-Preserving Medical Image Classification through Deep Learning and Matrix Decompositioncited by 0
  5. 2023VerA: Versatile Anonymization Applicable to Clinical Facial Photographscited by 0
  6. 2025FairDeFace: Evaluating the Fairness and Adversarial Robustness of Face Obfuscation Methodscited by 0
  7. 2025A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identificationcited by 0
  8. 2026Interpolation-Based Optimization for Enforcing lp-Norm Metric Differential Privacy in Continuous and Fine-Grained Domainscited by 0