Privacy-Preserving Adversarial Networks

Author

Ardhendu S. Tripathy, Missouri University of Science and TechnologyFollow
Ye Wang
Prakash Ishwar

Abstract

We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive information. Our approach employs adversarially-trained neural networks to implement randomized mechanisms and to perform a variational approximation of mutual information privacy. We validate our Privacy-Preserving Adversarial Networks (PPAN) framework via proof-of-concept experiments on discrete and continuous synthetic data, as well as the MNIST handwritten digits dataset. For synthetic data, our model-agnostic PPAN approach achieves tradeoff points very close to the optimal tradeoffs that are analytically-derived from model knowledge. In experiments with the MNIST data, we visually demonstrate a learned tradeoff between minimizing the pixel-level distortion versus concealing the written digit.

Recommended Citation

A. S. Tripathy et al., "Privacy-Preserving Adversarial Networks," 2019 57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019, pp. 495 - 505, Institute of Electrical and Electronics Engineers (IEEE), Sep 2019.

The definitive version is available at https://doi.org/10.1109/ALLERTON.2019.8919758

Department(s)

Computer Science

International Standard Book Number (ISBN)

978-172813151-1

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2019 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Sep 2019