mlsanityData to 7 Oct 2026

Towards Face Encryption by Generating Adversarial Identity Masks

arXiv 2003.06814 ↗First posted 15 Mar 2020cs.LG cs.CR cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

As billions of personal data being shared through social media and network, the data privacy and security have drawn an increasing attention. Several attempts have been made to alleviate the leakage of identity information from face photos, with the aid of, e.g., image obfuscation techniques. However, most of the present results are either perceptually unsatisfactory or ineffective against face recognition systems. Our goal in this paper is to develop a technique that can encrypt the personal photos such that they can protect users from unauthorized face recognition systems but remain visually identical to the original version for human beings. To achieve this, we propose a targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks which can be overlaid on facial images, such that the original identities can be concealed without sacrificing the visual quality. Extensive experiments demonstrate that TIP-IM provides 95%+ protection success rate against various state-of-the-art face recognition models under practical test scenarios. Besides, we also show the practical and effective applicability of our method on a commercial API service.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 16; 2024: 12; 2025: 10; 2026: 14.

62 papers.

Sort:

By area:

  1. 2022Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfercited by 77
  2. 2022A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challengescited by 45
  3. 2022Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognitioncited by 42
  4. 2023CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Searchcited by 42
  5. 2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 39
  6. 2023DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protectioncited by 34
  7. 2023Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognitioncited by 33
  8. 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protectioncited by 31
  9. 2021SoK: Anti-Facial Recognition Technologycited by 16
  10. 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attackscited by 13
  11. 2022Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognitioncited by 11
  12. 2023Learning with Noisy labels via Self-supervised Adversarial Noisy Maskingcited by 10
38 more
  1. 2024Personalized Privacy Protection Mask Against Unauthorized Facial Recognitioncited by 10
  2. 2022Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognitioncited by 8
  3. 2022Hiding Visual Information via Obfuscating Adversarial Perturbationscited by 7
  4. 2022Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentationcited by 7
  5. 2024Rethinking Impersonation and Dodging Attacks on Face Recognition Systemscited by 7
  6. 2024Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priorscited by 7
  7. 2025Enhancing Facial Privacy Protection via Weakening Diffusion Purificationcited by 7
  8. 2022Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigationcited by 6
  9. 2023Face Encryption via Frequency-Restricted Identity-Agnostic Attackscited by 6
  10. 20233D-Aware Adversarial Makeup Generation for Facial Privacy Protectioncited by 5
  11. 2023Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restorationcited by 5
  12. 2025Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protectioncited by 5
  13. 2023Detecting Adversarial Faces Using Only Real Face Self-Perturbationscited by 4
  14. 2023AdvCloak: Customized Adversarial Cloak for Privacy Protectioncited by 4
  15. 2024Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Modelscited by 4
  16. 2022Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protectioncited by 3
  17. 2023Attribute-Guided Encryption with Facial Texture Maskingcited by 3
  18. 2023AdvFAS: A robust face anti-spoofing framework against adversarial examplescited by 3
  19. 2024Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentationcited by 3
  20. 2023CamPro: Camera-based Anti-Facial Recognitioncited by 2
  21. 2024Proactive Schemes: A Survey of Adversarial Attacks for Social Goodcited by 2
  22. 2025DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategycited by 2
  23. 2025Non-Adaptive Adversarial Face Generationcited by 2
  24. 2025Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposurecited by 2
  25. 2023Group-based Robustness: A General Framework for Customized Robustness in the Real Worldcited by 1
  26. 2024Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulationcited by 1
  27. 2024Detecting Adversarial Data using Perturbation Forgerycited by 1
  28. 2024ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Modelscited by 1
  29. 2026Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemescited by 1
  30. 2026Machine Pareidolia: Protecting Facial Image with Emotional Editingcited by 1
  31. 2026FDeID-Toolbox: Face De-Identification Toolboxcited by 1
  32. 2026Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attackscited by 1
  33. 2026Flux-Guard: Facial Identity Protection using diffusion modelscited by 1
  34. 2023Facial Data Minimization: Shallow Model as Your Privacy Filtercited by 0
  35. 2023NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fieldscited by 0
  36. 2023VerA: Versatile Anonymization Applicable to Clinical Facial Photographscited by 0
  37. 2024Imperceptible Face Forgery Attack via Adversarial Semantic Maskcited by 0
  38. 2025Controllable Adversarial Makeup for Privacy via Text-Guided Diffusioncited by 0

50 most cited of 62 All 62 (JSON)