Crypto'Graph: Leveraging Privacy-Preserving Distributed Link Prediction for Robust Graph Learning

by   Sofiane Azogagh, et al.

Graphs are a widely used data structure for collecting and analyzing relational data. However, when the graph structure is distributed across several parties, its analysis is particularly challenging. In particular, due to the sensitivity of the data each party might want to keep their partial knowledge of the graph private, while still willing to collaborate with the other parties for tasks of mutual benefit, such as data curation or the removal of poisoned data. To address this challenge, we propose Crypto'Graph, an efficient protocol for privacy-preserving link prediction on distributed graphs. More precisely, it allows parties partially sharing a graph with distributed links to infer the likelihood of formation of new links in the future. Through the use of cryptographic primitives, Crypto'Graph is able to compute the likelihood of these new links on the joint network without revealing the structure of the private individual graph of each party, even though they know the number of nodes they have, since they share the same graph but not the same links. Crypto'Graph improves on previous works by enabling the computation of a certain number of similarity metrics without any additional cost. The use of Crypto'Graph is illustrated for defense against graph poisoning attacks, in which it is possible to identify potential adversarial links without compromising the privacy of the graphs of individual parties. The effectiveness of Crypto'Graph in mitigating graph poisoning attacks and achieving high prediction accuracy on a graph neural network node classification task is demonstrated through extensive experimentation on a real-world dataset.


page 1

page 2

page 3

page 4


Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective

Learning with graphs has attracted significant attention recently. Exist...

Privacy-Preserving Link Prediction

Consider two data holders, ABC and XYZ, with graph data (e.g., social ne...

Secure Evaluation of Knowledge Graph Merging Gain

Finding out the differences and commonalities between the knowledge of t...

When Differential Privacy Meets Graph Neural Networks

Graph Neural Networks have demonstrated superior performance in learning...

Link Prediction using Graph Neural Networks for Master Data Management

Learning graph representations of n-ary relational data has a number of ...

Assessing Centrality Without Knowing Connections

We consider the privacy-preserving computation of node influence in dist...

Asynchronous Distributed Learning from Constraints

In this paper, the extension of the framework of Learning from Constrain...

Please sign up or login with your details

Forgot password? Click here to reset