PuSH - Publication Server of Helmholtz Zentrum München: Differential privacy guarantees for analytics and machine learning on graphs: A survey of results.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Mueller, T.T.* ; Usynin, D.* ; Paetzold, J.C. ; Braren, R.* ; Rueckert, D.* ; Kaissis, G.

Differential privacy guarantees for analytics and machine learning on graphs: A survey of results.

J. Priv. Confid. 14, DOI: 10.29012/jpc.820 (2024)

Publ. Version/Full Text

DOI

Abstract
Metrics
Extra information

We study differential privacy (DP) in the context of graph-structured data and discuss its formulations and applications to the publication of graphs and their associated statistics, graph generation methods, and machine learning on graph-based data, including graph neural networks (GNNs). Interpreting DP guarantees in the context of graphstructured data can be challenging, as individual data points are interconnected (often non-linearly or sparsely). This differentiates graph databases from tabular databases, which are usually used in DP, and complicates related concepts like the derivation of per-sample gradients in GNNs. The problem is exacerbated by an absence of a single, well-established formulation of DP in graph settings. A lack of prior systematisation work motivated us to study graph-based learning from a privacy perspective. In this work, we systematise different formulations of DP on graphs, and discuss challenges and promising applications, including the GNN domain. We compare and separate works into methods that privately estimate graph data (either by statistical analysis or using GNNs), and methods that aim at generating new graph data. We conclude our work with a discussion of open questions and potential directions for further research in this area.

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

Keywords Differential Privacy ; Graph Analytics ; Graph Neural Networks ; Graph-structured Data

ISSN (print) / ISBN 2575-8527

e-ISSN 2575-8527

Journal Journal of Privacy and Confidentiality

Quellenangaben Volume: 14, Issue: 1

Publisher Cornell University Library

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Helmholtz AI - HMGU (HAI - HMGU)
Institute for Tissue Engineering and Regenerative Medicine (ITERM)