mlsanityData to 7 Oct 2026

OPOM: Customized Invisible Cloak towards Face Privacy Protection

arXiv 2205.11981 ↗First posted 24 May 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

While convenient in daily life, face recognition technologies also raise privacy concerns for regular users on the social media since they could be used to analyze face images and videos, efficiently and surreptitiously without any security restrictions. In this paper, we investigate the face privacy protection from a technology standpoint based on a new type of customized cloak, which can be applied to all the images of a regular user, to prevent malicious face recognition systems from uncovering their identity. Specifically, we propose a new method, named one person one mask (OPOM), to generate person-specific (class-wise) universal masks by optimizing each training sample in the direction away from the feature subspace of the source identity. To make full use of the limited training images, we investigate several modeling methods, including affine hulls, class centers, and convex hulls, to obtain a better description of the feature subspace of source identities. The effectiveness of the proposed method is evaluated on both common and celebrity datasets against black-box face recognition models with different loss functions and network architectures. In addition, we discuss the advantages and potential problems of the proposed method. In particular, we conduct an application study on the privacy protection of a video dataset, Sherlock, to demonstrate the potential practical usage of the proposed method. Datasets and code are available at https://github.com/zhongyy/OPOM.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 45 of its 64 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

45 of 64 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  9. 2016Adversarial examples in the physical worldcited by 1,762
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
33 more
  1. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2016Universal adversarial perturbationscited by 774
  4. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  5. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 633
  6. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  8. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  9. 2014Learning Face Representation from Scratchcited by 451
  10. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  11. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  12. 2018Deep Face Recognition: A Surveycited by 275
  13. 2017A Rewriting System for Convex Optimization Problemscited by 178
  14. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  15. 2014Deep Learning Face Representation by Joint Identification-Verificationcited by 162
  16. 2017Generative Adversarial Perturbationscited by 153
  17. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  18. 2018Generalizable Data-free Objective for Crafting Universal Adversarial Perturbationscited by 88
  19. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 79
  20. 2020When Machine Learning Meets Privacy: A Survey and Outlookcited by 67
  21. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 65
  22. 2017NAG: Network for Adversary Generationcited by 51
  23. 2019AnonymousNet: Natural Face De-Identification with Measurable Privacycited by 50
  24. 2019Live Face De-Identification in Videocited by 48
  25. 2017Level Playing Field for Million Scale Face Recognitioncited by 43
  26. 2017Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspectivecited by 38
  27. 2019Adversarial Learning with Margin-based Triplet Embedding Regularizationcited by 29
  28. 2020CD-UAP: Class Discriminative Universal Adversarial Perturbationcited by 27
  29. 2017Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturationcited by 21
  30. 2018From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Scriptcited by 20
  31. 2020Adversarial Privacy-preserving Filtercited by 13
  32. 2017Face Deidentification with Generative Deep Neural Networkscited by 8
  33. 2019A Method for Computing Class-wise Universal Adversarial Perturbationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 5; 2026: 5.

22 papers.

Sort:

By area:

  1. 2023CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Searchcited by 42
  2. 2024Transferable Adversarial Facial Images for Privacy Protectioncited by 26
  3. 2023Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregationcited by 22
  4. 2024Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customizationcited by 15
  5. 2024Personalized Privacy Protection Mask Against Unauthorized Facial Recognitioncited by 10
  6. 2023Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Frameworkcited by 9
  7. 2023Toward Face Biometric De-identification using Adversarial Examplescited by 8
  8. 2024Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priorscited by 7
  9. 2025Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protectioncited by 5
  10. 2023AdvCloak: Customized Adversarial Cloak for Privacy Protectioncited by 4
  11. 2025Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimizationcited by 3
  12. 2025DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategycited by 2
10 more
  1. 2025Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposurecited by 2
  2. 2024Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulationcited by 1
  3. 2026Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemescited by 1
  4. 2026Machine Pareidolia: Protecting Facial Image with Emotional Editingcited by 1
  5. 2023Facial Data Minimization: Shallow Model as Your Privacy Filtercited by 0
  6. 2023VerA: Versatile Anonymization Applicable to Clinical Facial Photographscited by 0
  7. 2025Controllable Adversarial Makeup for Privacy via Text-Guided Diffusioncited by 0
  8. 2026Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognitioncited by 0
  9. 2026Personalized Face Privacy Protection From a Single Imagecited by 0
  10. 2026Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecyclecited by 0