Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation

by   Xiaochen Zhu, et al.

Graph neural networks (GNNs) have gained an increasing amount of popularity due to their superior capability in learning node embeddings for various graph inference tasks, but training them can raise privacy concerns. To address this, we propose using link local differential privacy over decentralized nodes, enabling collaboration with an untrusted server to train GNNs without revealing the existence of any link. Our approach spends the privacy budget separately on links and degrees of the graph for the server to better denoise the graph topology using Bayesian estimation, alleviating the negative impact of LDP on the accuracy of the trained GNNs. We bound the mean absolute error of the inferred link probabilities against the ground truth graph topology. We then propose two variants of our LDP mechanism complementing each other in different privacy settings, one of which estimates fewer links under lower privacy budgets to avoid false positive link estimates when the uncertainty is high, while the other utilizes more information and performs better given relatively higher privacy budgets. Furthermore, we propose a hybrid variant that combines both strategies and is able to perform better across different privacy budgets. Extensive experiments show that our approach outperforms existing methods in terms of accuracy under varying privacy budgets.


Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks

Graph neural networks (GNNs) are susceptible to privacy inference attack...

Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach

Graph Neural Networks have achieved tremendous success in modeling compl...

VertexSerum: Poisoning Graph Neural Networks for Link Inference

Graph neural networks (GNNs) have brought superb performance to various ...

Node Injection Link Stealing Attack

In this paper, we present a stealthy and effective attack that exposes p...

A Deep Graph Neural Networks Architecture Design: From Global Pyramid-like Shrinkage Skeleton to Local Topology Link Rewiring

Expressivity plays a fundamental role in evaluating deep neural networks...

Releasing Graph Neural Networks with Differential Privacy Guarantees

With the increasing popularity of Graph Neural Networks (GNNs) in severa...

Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs

Graph Neural Networks (GNNs) are powerful tools for learning representat...

Please sign up or login with your details

Forgot password? Click here to reset