Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
Graph Machine Learning as a Service (GMLaaS) platforms increasingly implement explainability interfaces to meet regulatory transparency requirements. However, this transparency creates exploitable vulnerabilities for model extraction attacks. We present the first model extraction attack specifically designed for graph classification under strict black-box constraints where the attacker observes only discrete class labels and binary explanation masks (no probability scores, gradients, or confidence values). Our method (1) uses model explanation outputs to guide Monte Carlo edge sensitivity estimation toward decision boundaries, with Hoeffding concentration guarantees on estimation accuracy and (2) exploits explanation subgraphs to efficiently narrow the boundary search space. Extensive experiments on benchmark graph datasets across multiple domains demonstrate our method's superiority over comparable baselines. These findings demonstrate that such explainability interfaces create exploitable attack surfaces, informing both defensive mechanisms and policy frameworks for explainable AI mandates. The implementation code is provided in https://github.com/LabRAI/XSTEAL/.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph ClassificationModel extractionSimilar Papers 제목 키워드 기반
How Explanations Leak the Decision Logic: Stealing Graph Neural Networks via Explanation Alignment
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 AnalysisTrojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models
Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) align graph representations with language semantics to support transferable graph learning. Despite these advantages, the backdoor vulnerability of GFMs on …
Graph LearningLinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN
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…
EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. Howev…
Generating Skyline Explanations for Graph Neural Networks
This paper proposes a novel approach to generate subgraph explanations for graph neural networks GNNs that simultaneously optimize multiple measures for explainability. Existing GNN explanation methods often compute subg…
Explanation Generation