Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 166

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

AnonymousNet: Natural Face De-Identification With Measurable Privacy

Open access
Li, Tao, Lin, Lei · 2019 · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Abstract

With billions of personal images being generated from social media and cameras of all sorts on a daily basis, security and privacy are unprecedentedly challenged. Although extensive attempts have been made, existing face image de-identification techniques are either insufficient in photo-reality or incapable of balancing privacy and usability qualitatively and quantitatively, i.e., they fail to answer counterfactual questions such as "is it private now?", "how private is it?", and "can it be more private?" In this paper, we propose a novel framework called AnonymousNet, with an effort to address these issues systematically, balance usability, and enhance privacy in a natural and measurable manner. The framework encompasses four stages: facial attribute estimation, privacy-metric-oriented face obfuscation, directed natural image synthesis, and adversarial perturbation. Not only do we achieve the state-of-the-arts in terms of image quality and attribute prediction accuracy, we are also the first to show that facial privacy is measurable, can be factorized, and accordingly be manipulated in a photo-realistic fashion to fulfill different requirements and application scenarios. Experiments further demonstrate the effectiveness of the proposed framework.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvprw.2019.00013

Cites

20 of 20 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 46

  1. 10.1109/ICPR.2010.551 · DOI
  2. mcpherson, 2016, Defeating image obfuscation with deep learning
  3. 10.1109/ICME.2012.26 · DOI
  4. liaw, 2002, Classification and regression by randomforest, R News, 2, 18
  5. 10.1109/CVPRW.2017.176 · DOI
  6. 10.1109/CVPRW.2018.00209 · DOI
  7. 10.1109/ICDE.2006.1 · DOI · Paper page
  8. 10.1109/ICCV.2015.425 · DOI · Paper page
  9. 10.1109/CVPRW.2019.00034 · DOI
  10. liu, 0, Coupled generative adversarial networks, Advances in neural information processing systems, 469
  11. wu, 2018, Privacy-protective-gan for face de-identification
  12. 10.1109/CVPR.2017.728 · DOI · Paper page
  13. zhang, 2018, Privacy-preserving machine learning through data obfuscation
  14. li, 0, AutoMPC: Efficient multiparty computation for secure and privacy-preserving cooperative control of connected autonomous vehicles, Proceedings of the Artificial Intelligence Safety Workshop (SafeAI) of the Thirty-Third AAAI Conference on Artificial Intelligence
  15. 10.1007/978-3-319-10599-4_7 · DOI · Paper page
  16. li, 0, Toward robust and efficient training of generative adversarial networks with bayesian approximation, the Approximation Theory and Machine Learning Conference
  17. 10.1109/BigData.2018.8622140 · DOI
  18. 10.1109/ICCV.2011.6126275 · DOI
  19. 10.1145/342009.335438 · DOI · Paper page
  20. karras, 2017, Progressive growing of GANs for improved quality stability and variation
  21. 10.1109/CVPRW.2017.254 · DOI · Paper page
  22. li, 0, Beauty learning and counterfactual inference, CVPR-19 Workshop on Explainable AI
  23. li, 2017, SoK Single image super-resolution
  24. samarati, 1998, Protecting Privacy when Disclosing Information k-anonymity and its Enforcement Through Generalization and Suppression
  25. 10.1109/35.312842 · DOI · Paper page
  26. 10.1145/3168389 · DOI · Paper page
  27. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  28. 10.1142/S021848850200165X · DOI · Paper page
  29. 10.1109/CVPR.2013.446 · DOI · Paper page
  30. 10.1109/CVPR.2018.00530 · DOI · Paper page
  31. goodfellow, 2019, 4 5 years of GAN progress on face generation
  32. goodfellow, 0, Generative adversarial nets, Advances in neural information processing systems, 2672
  33. 10.1007/11767831_15 · DOI
  34. 10.1145/3173574.3173621 · DOI
  35. 10.1109/CVPRW.2017.175 · DOI
  36. johnson, 0, Perceptual losses for real-time style transfer and super-resolution, European Conference on Computer Vision, 694
  37. 10.1145/1399504.1360638 · DOI
  38. 10.1109/CVPR.2018.00047 · DOI · Paper page
  39. 10.1007/s11263-015-0816-y · DOI · Paper page
  40. dwork, 2011, Differential privacy, Encyclopedia of Cryptography and Security, 338, 10.1007/978-1-4419-5906-5_752 · DOI · Paper page
  41. 10.1109/FG.2011.5771409 · doi:10.1109/fg.2011.5771409
  42. 10.1007/978-3-319-46454-1_2 · DOI
  43. 10.1023/A:1026543900054 · DOI · Paper page
  44. 10.1109/TKDE.2005.32 · DOI · Paper page
  45. 10.1109/ICCV.2017.165 · DOI
  46. 10.1007/978-3-319-46487-9_2 · DOI

Cited by

See all 166

Metadata

Authors
Li, T., & Lin, L.
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher
IEEE
Published
2019-06
Pages
56-65
OpenAlex
W2977362526
Cited by
166
References
20
FWCI
6.58
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.