paper-with-me

홈 › Papers

Node Injection Link Stealing Attack

2023-07-25 · Oualid Zari, Javier Parra-Arnau, Ayşe Ünsal, Melek Önen

In this paper, we present a stealthy and effective attack that exposes privacy vulnerabilities in Graph Neural Networks (GNNs) by inferring private links within graph-structured data. Focusing on the inductive setting where new nodes join the graph and an API is used to query predictions, we investigate the potential leakage of private edge information. We also propose methods to preserve privacy while maintaining model utility. Our attack demonstrates superior performance in inferring the links compared to the state of the art. Furthermore, we examine the application of differential privacy (DP) mechanisms to mitigate the impact of our proposed attack, we analyze the trade-off between privacy preservation and model utility. Our work highlights the privacy vulnerabilities inherent in GNNs, underscoring the importance of developing robust privacy-preserving mechanisms for their application.

📄 PDF Abstract BibTeX arXiv:2307.13548

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Similar Papers 제목 키워드 기반

Large Language Models for Link Stealing Attacks Against Graph Neural Networks

2024-06-22 · Faqian Guan, Tianqing Zhu, Hui Sun, Wanlei Zhou 외

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for ha…

Recommendation Systems

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models

2025-01-19 · Jiadong Lou, Xu Yuan, Rui Zhang, Xingliang Yuan 외

Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. However, they encounter the potential vulnerability from the link stealing attacks, which can inf…

Prediction

Link Stealing Attacks Against Inductive Graph Neural Networks

2024-05-09 · Yixin Wu, Xinlei He, Pascal Berrang, Mathias Humbert 외

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 indu…

Graph Neural Network

LinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN

2024-10-01 · Yuxing Zhang, Siyuan Meng, Chunchun Chen, Mengyao Peng 외

Graph neural networks(GNNs) have a wide range of applications in multimedia.Recent studies have shown that Graph neural networks(GNNs) are vulnerable to link stealing attacks,which infers the existence of edges in the ta…

How Feasible is Augmenting Fake Nodes with Learnable Features as a Counter-strategy against Link Stealing Attacks?

2025-03-12 · Mir Imtiaz Mostafiz, Imtiaz Karim, Elisa Bertino

Graph Neural Networks (GNNs) are widely used and deployed for graph-based prediction tasks. However, as good as GNNs are for learning graph data, they also come with the risk of privacy leakage. For instance, an attacker…

Graph Embedding