paper-with-me

홈 › Papers

On Stealing Graph Neural Network Models

2025-11-10 · Marcin Podhajski, Jan Dubiński, Franziska Boenisch, Adam Dziedzic, Agnieszka Pręgowska, Tomasz P. Michalak arxiv

Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate how an adversary can extract a GNN with very limited interactions with the model. Our approach first enables the adversary to obtain the model backbone without making direct queries to the victim model and then to strategically utilize a fixed query limit to extract the most informative data. The experiments on eight real-world datasets demonstrate the effectiveness of the attack, even under a very restricted query limit and under defense against model extraction in place. Our findings underscore the need for robust defenses against GNN model extraction threats.

📄 PDF Abstract BibTeX arXiv:2511.07170

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural NetworkModel extraction

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

Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks

2024-05-20 · Marcin Podhajski, Jan Dubiński, Franziska Boenisch, Adam Dziedzic 외

Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing of graph-structured data without relying…

Contrastive Learning

Stealing Links from Graph Neural Networks

2020-05-05 · Xinlei He, Jinyuan Jia, Michael Backes, Neil Zhenqiang Gong 외

Graph data, such as chemical networks and social networks, may be deemed confidential/private because the data owner often spends lots of resources collecting the data or the data contains sensitive information, e.g., so…

Fraud DetectionRecommendation Systems

Model Stealing Attacks Against Inductive Graph Neural Networks

2021-12-15 · Yun Shen, Xinlei He, Yufei Han, Yang Zhang

Many real-world data come in the form of graphs. Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications. In particular, …

model

How Explanations Leak the Decision Logic: Stealing Graph Neural Networks via Explanation Alignment

2025-06-03 · Bin Ma, Yuyuan Feng, Minhua Lin, Enyan Dai

Graph Neural Networks (GNNs) have become essential tools for analyzing graph-structured data in domains such as drug discovery and financial analysis, leading to growing demands for model transparency. Recent advances in…

Data AugmentationDrug DiscoveryFinancial Analysis