PuSH - Publication Server of Helmholtz Zentrum München: Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Kaissis, G. ; Ziller, A.* ; Kolek, S.* ; Riess, A. ; Rueckert, D.*

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning.

In: (37th Conference on Neural Information Processing Systems (NeurIPS), 10-16 December 2023, New Orleans, LA). 10010 North Torrey Pines Rd, La Jolla, California 92037 Usa: Neural Information Processing Systems (nips), 2023. 24

Abstract
Metrics
Extra information

Differentially private mechanisms restrict the membership inference capabilities of powerful (optimal) adversaries against machine learning models. Such adversaries are rarely encountered in practice. In this work, we examine a more realistic threat model relaxation, where (sub-optimal) adversaries lack access to the exact model training database, but may possess related or partial data. We then formally characterise and experimentally validate adversarial membership inference capabilities in this setting in terms of hypothesis testing errors. Our work helps users to interpret the privacy properties of sensitive data processing systems under realistic threat model relaxations and choose appropriate noise levels for their use-case.

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Conference contribution

Corresponding Author

ISSN (print) / ISBN 1049-5258

Conference Title 37th Conference on Neural Information Processing Systems (NeurIPS)

Conference Date 10-16 December 2023

Conference Location New Orleans, LA

Quellenangaben Pages: 24

Publisher Neural Information Processing Systems (nips)

Publishing Place 10010 North Torrey Pines Rd, La Jolla, California 92037 Usa

Non-patent literature Publications

Institute(s) Institute for Machine Learning in Biomed Imaging (IML)

Grants German Federal Ministry of Education and Research
Konrad Zuse School of Excellence in Reliable AI (RelAI)
Bavarian State Ministry for Science and the Arts through the Munich Centre for Machine Learning (MCML)
Helmholtz Junior Research Group grant