University of Twente Student Theses

Login

Generative adversarial models for privacy-preserving release mechanisms

Vasterd, M.F.J. (2021) Generative adversarial models for privacy-preserving release mechanisms.

This is the latest version of this item.

[img] PDF
2MB
Abstract:Since the advancements of the Generave Adversarial Networks, many works have been proposed to better guarantee privacy in privacy-preserving release mechanisms. In this thesis, the current measures for privacy-leakage will be compared and studied in a practical experiment. This thesis uses the paper of Tripathy2017 et al. as a baseline, studies it, and continues their work by comparing their privacy-leakage measure mutual information to two other existing measures: Maximal Leakage and (Maximal) Alpha-Leakage. We start this work by reconstructing the paper of Tripathy et al, and find that this is not trivial. And the results are less promising then they appear in their paper. Furthermore, we show a generalized version of their work so that privacy-leakage measures other than mutual information are adaptable. Finally, we show how a generative adversarial network is trained on bivariate binary data using the maximal leakage and $\alpha$-leakage measures, and show the relation between $\alpha=1$ with mutual information and $\alpha=\infty$ with maximal leakage.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science MSc (60300)
Link to this item:http://purl.utwente.nl/essays/85542
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page