mlsanityData to 14 Oct 2026

Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protection

arXiv 2208.10688 ↗First posted 23 Aug 2022cs.CV cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Billions of people are sharing their daily life images on social media every day. However, their biometric information (e.g., fingerprint) could be easily stolen from these images. The threat of fingerprint leakage from social media raises a strong desire for anonymizing shared images while maintaining image qualities, since fingerprints act as a lifelong individual biometric password. To guard the fingerprint leakage, adversarial attack emerges as a solution by adding imperceptible perturbations on images. However, existing works are either weak in black-box transferability or appear unnatural. Motivated by visual perception hierarchy (i.e., high-level perception exploits model-shared semantics that transfer well across models while low-level perception extracts primitive stimulus and will cause high visual sensitivities given suspicious stimulus), we propose FingerSafe, a hierarchical perceptual protective noise injection framework to address the mentioned problems. For black-box transferability, we inject protective noises on fingerprint orientation field to perturb the model-shared high-level semantics (i.e., fingerprint ridges). Considering visual naturalness, we suppress the low-level local contrast stimulus by regularizing the response of Lateral Geniculate Nucleus. Our FingerSafe is the first to provide feasible fingerprint protection in both digital (up to 94.12%) and realistic scenarios (Twitter and Facebook, up to 68.75%). Our code can be found at https://github.com/nlsde-safety-team/FingerSafe.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 94 references that are in the map. First posted on arXiv 23 Aug 2022.

Builds on

33 of 94 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  12. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
21 more
  1. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  2. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  3. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  4. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 362
  5. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  6. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  7. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 209
  8. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 193
  9. 2014Deep Learning Face Representation by Joint Identification-Verificationcited by 162
  10. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  11. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  12. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 94
  13. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 87
  14. 2020Towards Face Encryption by Generating Adversarial Identity Maskscited by 63
  15. 2019Training Robust Deep Neural Networks via Adversarial Noise Propagationcited by 62
  16. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  17. 2016Defeating Image Obfuscation with Deep Learningcited by 43
  18. 2017FingerNet: An Unified Deep Network for Fingerprint Minutiae Extractioncited by 36
  19. 2016Faceless Person Recognition; Privacy Implications in Social Mediacited by 27
  20. 2021Mobile Touchless Fingerprint Recognition: Implementation, Performance and Usability Aspectscited by 10
  21. 2016Can we still avoid automatic face detection?cited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 1; 2026: 1.

3 papers.

  1. 2023Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attackscited by 10
  2. 2025Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse Synthesiscited by 0
  3. 2026Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognitioncited by 0