Corpus ID: 203592046

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

@article{Ilanchezian2019MaximalAP,
  title={Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest},
  author={Indu Ilanchezian and Praneeth Vepakomma and Abhishek Singh and Otkrist Gupta and G. N. S. Prasanna and R. Raskar},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.12734}
}
In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection. We employ adversarial perturbations for obfuscating certain variables in raw data while preserving the rest. Current adversarial perturbation methods are used for data poisoning with minimal perturbations of the raw data such that the machine learning model's performance is adversely impacted while the human vision cannot perceive the… Expand

References

SHOWING 1-10 OF 23 REFERENCES
Explaining and Harnessing Adversarial Examples
  • 6,767
  • PDF
Adversarial Removal of Gender from Deep Image Representations
  • 11
  • PDF
Synthesizing Robust Adversarial Examples
  • 706
  • PDF
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
  • 60
  • PDF
Distributed generation of privacy preserving data with user customization
  • 6
  • PDF
Generating User-friendly Explanations for Loan Denials using GANs
  • 4
  • PDF
GARP-face: Balancing privacy protection and utility preservation in face de-identification
  • 45
  • PDF
Privacy-Protective-GAN for Face De-identification
  • 28
  • PDF
...
1
2
3
...