Every Query Counts: Analyzing the Privacy Loss of Exploratory Data Analyses
Machine Learning
2021-07-15 v1 Cryptography and Security
Machine Learning
Abstract
An exploratory data analysis is an essential step for every data analyst to gain insights, evaluate data quality and (if required) select a machine learning model for further processing. While privacy-preserving machine learning is on the rise, more often than not this initial analysis is not counted towards the privacy budget. In this paper, we quantify the privacy loss for basic statistical functions and highlight the importance of taking it into account when calculating the privacy-loss budget of a machine learning approach.
Keywords
Cite
@article{arxiv.2008.12282,
title = {Every Query Counts: Analyzing the Privacy Loss of Exploratory Data Analyses},
author = {Saskia Nuñez von Voigt and Mira Pauli and Johanna Reichert and Florian Tschorsch},
journal= {arXiv preprint arXiv:2008.12282},
year = {2021}
}
Comments
Accepted Paper for DPM 2020 co-located ESORICS 2020