Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy

Authors: Georgios Kaissis, Jamie Hayes, Alexander Ziller, Daniel Rueckert
Published: 2023-07-08

Source: https://arxiv.org/abs/2307.03928

PDF: https://arxiv.org/pdf/2307.03928

AIにより推定されたラベル

アルゴリズム設計 データの隠蔽 セキュリティ保証

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models. Previous research has demonstrated that differential privacy (DP) mechanisms also provide ReRo, but so far, only asymptotic Monte Carlo estimates of a tight ReRo bound have been shown. Directly computable ReRo bounds for general DP mechanisms are thus desirable. In this work, we establish a connection between hypothesis testing DP and ReRo and derive closed-form, analytic or numerical ReRo bounds for the Laplace and Gaussian mechanisms and their subsampled variants.