ML Anthology

Protecting Visual Secrets Using Adversarial Nets

Nisarg Raval, Ashwin Machanavajjhala, Landon P. Cox
CVPRW 2017 pp. 1329-1332
doi:10.1109/CVPRW.2017.174 /cvprw/2017/raval2017cvprw-protecting/

Abstract

Protecting visual secrets is an important problem due to the prevalence of cameras that continuously monitor our surroundings. Any viable solution to this problem should also minimize the impact on the utility of applications that use images. In this work, we build on the existing work of adversarial learning to design a perturbation mechanism that jointly optimizes privacy and utility objectives. We provide a feasibility study of the proposed mechanism and present ideas on developing a privacy framework based on the adversarial perturbation mechanism.

CVPRW Semantic Scholar

Cite

Text

Raval et al. "Protecting Visual Secrets Using Adversarial Nets." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.174

Markdown

[Raval et al. "Protecting Visual Secrets Using Adversarial Nets." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/raval2017cvprw-protecting/) doi:10.1109/CVPRW.2017.174

BibTeX

@inproceedings{raval2017cvprw-protecting,
  title     = {{Protecting Visual Secrets Using Adversarial Nets}},
  author    = {Raval, Nisarg and Machanavajjhala, Ashwin and Cox, Landon P.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {1329-1332},
  doi       = {10.1109/CVPRW.2017.174},
  url       = {https://mlanthology.org/cvprw/2017/raval2017cvprw-protecting/}
}