Exact and Efficient Bayesian Inference for Privacy Risk Quantification

Rasmus Carl Rønneberg, Raúl Pardo, Andrzej Wasowski

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

Data analysis has high value both for commercial and research purposes. However, disclosing analysis results may pose severe privacy risk to individuals. Privug is a method to quantify privacy risks of data analytics programs by analyzing their source code. The method uses probability distributions to model attacker knowledge and Bayesian inference to update said knowledge based on observable outputs. Currently, Privug uses Markov Chain Monte Carlo (MCMC) to perform inference, which is a flexible but approximate solution. This paper presents an exact Bayesian inference engine based on multivariate Gaussian distributions to accurately and efficiently quantify privacy risks. The inference engine is implemented for a subset of Python programs that can be modeled as multivariate Gaussian models. We evaluate the method by analyzing privacy risks in programs to release public statistics. The evaluation shows that our method accurately and efficiently analyzes privacy risks, and outperforms existing methods. Furthermore, we demonstrate the use of our engine to analyze the effect of differential privacy in public statistics.
Original languageEnglish
Title of host publicationProceedings of Software Engineering and Formal Methods (SEFM'23)
Number of pages18
Volume14323
PublisherSpringer, Cham
Publication date31 Oct 2023
Pages263-281
ISBN (Print)978-3-031-47114-8
ISBN (Electronic)978-3-031-47115-5
DOIs
Publication statusPublished - 31 Oct 2023
Event21st International Conference on Software Engineering and Formal Methods - Eindhoven, Netherlands
Duration: 6 Nov 202310 Nov 2023
https://sefm-conference.github.io/2023/

Conference

Conference21st International Conference on Software Engineering and Formal Methods
Country/TerritoryNetherlands
CityEindhoven
Period06/11/202310/11/2023
Internet address
SeriesLecture Notes in Computer Science
ISSN0302-9743

Fingerprint

Dive into the research topics of 'Exact and Efficient Bayesian Inference for Privacy Risk Quantification'. Together they form a unique fingerprint.

Cite this