Privacy Leakage in Graph Embedding - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Privacy Leakage in Graph Embedding

(1) , (1) , (2)
1
2

Abstract

Graph embeddings have been proposed to map graph data to low dimensional space for downstream processing (e.g., node classification or link prediction). With the increasing collection of personal data, graph embeddings can be trained on private and sensitive data. For the first time, we quantify the privacy leakage in graph embeddings through three inference attacks targeting Graph Neural Networks. We propose a membership inference attack to infer whether a graph node corresponding to individual user's data was member of the model's training or not. We consider a blackbox setting where the adversary exploits the output prediction scores, and a whitebox setting where the adversary has also access to the released node embeddings. This attack provides an accuracy up to 28% (blackbox) 36% (whitebox) beyond random guess by exploiting the distinguishable footprint between train and test data records left by the graph embedding. We propose a Graph Reconstruction attack where the adversary aims to reconstruct the target graph given the corresponding graph embeddings. Here, the adversary can reconstruct the graph with more than 80% of accuracy and link inference between two nodes around 30% more confidence than a random guess. We then propose an attribute inference attack where the adversary aims to infer a sensitive attribute. We show that graph embeddings are strongly correlated to node attributes letting the adversary inferring sensitive information (e.g., gender or location).
Fichier principal
Vignette du fichier
paper.pdf (755.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02956397 , version 1 (02-10-2020)

Identifiers

  • HAL Id : hal-02956397 , version 1

Cite

Vasisht Duddu, Antoine Boutet, Virat Shejwalkar. Privacy Leakage in Graph Embedding. 2020. ⟨hal-02956397⟩
96 View
373 Download

Share

Gmail Facebook Twitter LinkedIn More