Obfuscation via Information Density Estimation

Hsiang Hsu, Shahab Asoodeh, Flavio Calmon
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:906-917, 2020.

Abstract

Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities exceed a pre-defined threshold are deemed information-leaking features. Once these features are identified, we sequentially pass them through a targeted obfuscation mechanism with a provable leakage guarantee in terms of $\mathsf{E}_\gamma$-divergence. The core of this mechanism relies on a data-driven estimate of the trimmed information density for which we propose a novel estimator, named the \textit{trimmed information density estimator} (TIDE). We then use TIDE to implement our mechanism on three real-world datasets. Our approach can be used as a data-driven pipeline for designing obfuscation mechanisms targeting specific features.

Cite this Paper

BibTeX
@InProceedings{pmlr-v108-hsu20a, title = {Obfuscation via Information Density Estimation}, author = {Hsu, Hsiang and Asoodeh, Shahab and Calmon, Flavio}, booktitle = {Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics}, pages = {906--917}, year = {2020}, editor = {Chiappa, Silvia and Calandra, Roberto}, volume = {108}, series = {Proceedings of Machine Learning Research}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/hsu20a/hsu20a.pdf}, url = {https://proceedings.mlr.press/v108/hsu20a.html}, abstract = {Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities exceed a pre-defined threshold are deemed information-leaking features. Once these features are identified, we sequentially pass them through a targeted obfuscation mechanism with a provable leakage guarantee in terms of $\mathsf{E}_\gamma$-divergence. The core of this mechanism relies on a data-driven estimate of the trimmed information density for which we propose a novel estimator, named the \textit{trimmed information density estimator} (TIDE). We then use TIDE to implement our mechanism on three real-world datasets. Our approach can be used as a data-driven pipeline for designing obfuscation mechanisms targeting specific features.} }
Endnote
%0 Conference Paper %T Obfuscation via Information Density Estimation %A Hsiang Hsu %A Shahab Asoodeh %A Flavio Calmon %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-hsu20a %I PMLR %P 906--917 %U https://proceedings.mlr.press/v108/hsu20a.html %V 108 %X Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities exceed a pre-defined threshold are deemed information-leaking features. Once these features are identified, we sequentially pass them through a targeted obfuscation mechanism with a provable leakage guarantee in terms of $\mathsf{E}_\gamma$-divergence. The core of this mechanism relies on a data-driven estimate of the trimmed information density for which we propose a novel estimator, named the \textit{trimmed information density estimator} (TIDE). We then use TIDE to implement our mechanism on three real-world datasets. Our approach can be used as a data-driven pipeline for designing obfuscation mechanisms targeting specific features.
APA
Hsu, H., Asoodeh, S. & Calmon, F.. (2020). Obfuscation via Information Density Estimation. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 108:906-917 Available from https://proceedings.mlr.press/v108/hsu20a.html.

Related Material