Skip to yearly menu bar Skip to main content


Poster

Provable Privacy with Non-Private Pre-Processing

Yaxi Hu · Amartya Sanyal · Bernhard Schölkopf

Hall C 4-9 #2106
[ ] [ Paper PDF ]
Thu 25 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

When analyzing Differentially Private (DP) machine learning pipelines, the potential privacy cost of data-dependent pre-processing is frequently overlooked in privacy accounting. In this work, we propose a general framework to evaluate the additional privacy cost incurred by non-private data-dependent pre-processing algorithms. Our framework establishes upper bounds on the overall privacy guarantees by utilising two new technical notions: a variant of DP termed Smooth DP and the bounded sensitivity of the pre-processing algorithms. In addition to the generic framework, we provide explicit overall privacy guarantees for multiple data-dependent pre-processing algorithms, such as data imputation, quantization, deduplication, standard scaling and PCA, when used in combination with several DP algorithms. Notably, this framework is also simple to implement, allowing direct integration into existing DP pipelines.

Chat is not available.