Corpus ID: 91184652

Generating Optimal Privacy-Protection Mechanisms via Machine Learning

@article{Romanelli2019GeneratingOP,
  title={Generating Optimal Privacy-Protection Mechanisms via Machine Learning},
  author={Marco Romanelli and C. Palamidessi and K. Chatzikokolakis},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.01059}
}
We consider the problem of obfuscating sensitive information while preserving utility. Given that an analytical solution is often not feasible because of un-scalability and because the background knowledge may be too complicated to determine, we propose an approach based on machine learning, inspired by the GANs (Generative Adversarial Networks) paradigm. The idea is to set up two nets: the generator, that tries to produce an optimal obfuscation mechanism to protect the data, and the classifier… Expand
7 Citations
Agnostic data debiasing through a local sanitizer learnt from an adversarial network approach
  • 1
  • PDF
A Siamese Adversarial Anonymizer for Data Minimization in Biometric Applications
  • PDF
Estimating g-Leakage via Machine Learning
  • 1
  • PDF

References

SHOWING 1-10 OF 33 REFERENCES
Privacy Games: Optimal User-Centric Data Obfuscation
  • R. Shokri
  • Computer Science
  • Proc. Priv. Enhancing Technol.
  • 2015
  • 91
  • PDF
On the information leakage of differentially-private mechanisms
  • 12
  • PDF
Privacy-Preserving Adversarial Networks
  • 44
  • PDF
On the Bayes risk in information-hiding protocols
  • 89
  • PDF
Censoring Representations with an Adversary
  • 261
  • PDF
Calibrating Noise to Sensitivity in Private Data Analysis
  • 4,225
  • PDF
AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
  • J. Jia, N. Gong
  • Computer Science, Mathematics
  • USENIX Security Symposium
  • 2018
  • 59
  • PDF
On privacy-utility tradeoffs for constrained data release mechanisms
  • 40
  • PDF
...
1
2
3
4
...