PuSH - Publication Server of Helmholtz Zentrum München: Accessibility of covariance information creates vulnerability in Federated Learning frameworks.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Huth, M. ; Arruda, J.* ; Gusinow, R. ; Contento, L.* ; Tacconelli, E.* ; Hasenauer, J.*

Accessibility of covariance information creates vulnerability in Federated Learning frameworks.

Bioinformatics 39:9 (2023)

Publ. Version/Full Text

DOI

PMC

Abstract
Metrics
Extra information

MOTIVATION: Federated Learning (FL) is gaining traction in various fields as it enables integrative data analysis without sharing sensitive data, such as in healthcare. However, the risk of data leakage caused by malicious attacks must be considered. In this study, we introduce a novel attack algorithm that relies on being able to compute sample means, sample covariances, and construct known linearly independent vectors on the data owner side. RESULTS: We show that these basic functionalities, which are available in several established FL frameworks, are sufficient to reconstruct privacy-protected data. Additionally, the attack algorithm is robust to defense strategies that involve adding random noise. We demonstrate the limitations of existing frameworks and propose potential defense strategies analyzing the implications of using differential privacy. The novel insights presented in this study will aid in the improvement of FL frameworks. AVAILABILITY AND IMPLEMENTATION: The code examples are provided at GitHub (https://github.com/manuhuth/Data-Leakage-From-Covariances.git). The CNSIM1 dataset, which we used in the manuscript, is available within the DSData R package (https://github.com/datashield/DSData/tree/main/data).

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

ISSN (print) / ISBN 1367-4803

Journal Bioinformatics

Quellenangaben Volume: 39, Issue: 9 Article Number: 9

Publisher Oxford University Press

Publishing Place Oxford

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Institute of Computational Biology (ICB)

Grants European Union
ORCHESTRA project
Helmholtz Association-Munich School for Data Science (MUDS)
University of Bonn
German Ministry for Education and Research (Deutches Bundesminsterium fur Bildung und Forschung, BMBF)
German Research Foundation (Deutsche Forschungsgemeinschaft, DFG)