Link Stealing Attacks Against Inductive Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, including the transductive setting and the inductive setting. In the transductive setting, the trained model can only predict the labels of nodes that were observed at the training time. In the inductive setting, the trained model can be generalized to new nodes/graphs. Due to its flexibility, the inductive setting is the most popular GNN setting at the moment. Previous work has shown that transductive GNNs are vulnerable to a series of privacy attacks. However, a comprehensive privacy analysis of inductive GNN models is still missing. This paper fills the gap by conducting a systematic privacy analysis of inductive GNNs through the lens of link stealing attacks, one of the most popular attacks that are specifically designed for GNNs. We propose two types of link stealing attacks, i.e., posterior-only attacks and combined attacks. We define threat models of the posterior-only attacks with respect to node topology and the combined attacks by considering combinations of posteriors, node attributes, and graph features. Extensive evaluation on six real-world datasets demonstrates that inductive GNNs leak rich information that enables link stealing attacks with advantageous properties. Even attacks with no knowledge about graph structures can be effective. We also show that our attacks are robust to different node similarities and different graph features. As a counterpart, we investigate two possible defenses and discover they are ineffective against our attacks, which calls for more effective defenses.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 9 May 2024.
Builds on
32 of 45 references.
References · 32
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2015Image-based Recommendations on Styles and Substitutescited by 702
- 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
- 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
- 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
- 2018Adversarial Attack on Graph Structured Datacited by 300
20 more
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2020Backdoor Attacks to Graph Neural Networkscited by 126
- 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
- 2020Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Modelscited by 116
- 2020Stealing Links from Graph Neural Networkscited by 114
- 2020Graph Backdoorcited by 112
- 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
- 2020Quantifying Privacy Leakage in Graph Embeddingcited by 82
- 2021Membership Inference Attack on Graph Neural Networkscited by 81
- 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
- 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
- 2021LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysiscited by 65
- 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
- 2021Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implicationscited by 50
- 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
- 2019Adversarial Model Extraction on Graph Neural Networkscited by 22
- 2017Practical Attacks Against Graph-based Clusteringcited by 9
- 2017walk2friends: Inferring Social Links from Mobility Profilescited by 7
- 2023VertexSerum: Poisoning Graph Neural Networks for Link Inferencecited by 5
- 2018Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Networkcited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.