Conference
Obfuscation via Information Density Estimation
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 …
Authors
Hsu H; Asoodeh S; Calmon FP
Volume
108
Pagination
pp. 906-917
Publication Date
January 1, 2020
Conference proceedings
Proceedings of Machine Learning Research