LPGNet: Link Private Graph Networks for Node Classification

by   Aashish Kolluri, et al.

Classification tasks on labeled graph-structured data have many important applications ranging from social recommendation to financial modeling. Deep neural networks are increasingly being used for node classification on graphs, wherein nodes with similar features have to be given the same label. Graph convolutional networks (GCNs) are one such widely studied neural network architecture that perform well on this task. However, powerful link-stealing attacks on GCNs have recently shown that even with black-box access to the trained model, inferring which links (or edges) are present in the training graph is practical. In this paper, we present a new neural network architecture called LPGNet for training on graphs with privacy-sensitive edges. LPGNet provides differential privacy (DP) guarantees for edges using a novel design for how graph edge structure is used during training. We empirically show that LPGNet models often lie in the sweet spot between providing privacy and utility: They can offer better utility than "trivially" private architectures which use no edge information (e.g., vanilla MLPs) and better resilience against existing link-stealing attacks than vanilla GCNs which use the full edge structure. LPGNet also offers consistently better privacy-utility tradeoffs than DPGCN, which is the state-of-the-art mechanism for retrofitting differential privacy into conventional GCNs, in most of our evaluated datasets.


page 1

page 2

page 3

page 4


Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks

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

Secure Network Release with Link Privacy

Many data mining and analytical tasks rely on the abstraction of network...

LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis

Graph structured data have enabled several successful applications such ...

Node Injection Link Stealing Attack

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

Novel Edge and Density Metrics for Link Cohesion

We present a new metric of link cohesion for measuring the strength of e...

Edge Differential Privacy for Algebraic Connectivity of Graphs

Graphs are the dominant formalism for modeling multi-agent systems. The ...

Community Preserved Social Graph Publishing with Node Differential Privacy

The goal of privacy-preserving social graph publishing is to protect ind...

Please sign up or login with your details

Forgot password? Click here to reset