Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective

@article{Oh2017AdversarialIP,
  title={Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective},
  author={Seong Joon Oh and Mario Fritz and Bernt Schiele},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={1491-1500}
}
  • Seong Joon Oh, Mario Fritz, Bernt Schiele
  • Published 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • Users like sharing personal photos with others through social media. [...] Key Method We introduce a general game theoretical framework for the user-recogniser dynamics, and present a case study that involves current state of the art AIP and person recognition techniques. We derive the optimal strategy for the user that assures an upper bound on the recognition rate independent of the recogniser’s counter measure. Code is available at https://goo.gl/hgvbNK.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 59 CITATIONS

    Towards Privacy Protection by Generating Adversarial Identity Masks

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Generative adversarial network based image privacy protection algorithm

    VIEW 8 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    AnonymousNet: Natural Face De-Identification With Measurable Privacy

    • Tao Li, Lei Lin
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
    • 2019
    VIEW 1 EXCERPT
    CITES BACKGROUND

    Privacy Adversarial Network

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 4 Highly Influenced Citations

    • Averaged 17 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    Adversarial examples in the physical world

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Assessing Threat of Adversarial Examples on Deep Neural Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Adversarial Diversity and Hard Positive Generation

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Universal Adversarial Perturbations

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Can we still avoid automatic face detection?