Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?

[2605.30470] Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks? Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2605.30470 (cs) [Submitted on 28 May 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks? Authors: Ojas Nimase , Jiate Li , Yue Zhao , Yushun Dong View PDF HTML (experimental) Abstract: 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 this https URL . Comments: 28 pages, 8 figures, 10 tables. Under review at NeurIPS 2026 Subjects: Machine Learning (cs.LG) Cite as: arXiv:2605.30470 [cs.LG] (or arXiv:2605.30470v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2605.30470 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ojas Nimase [ view email ] [v1] Thu, 28 May 2026 18:41:20 UTC (7,104 KB) [v2] Fri, 28 Aug 2026 02:12:38 UTC (7,104 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-05 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?#682700
• A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit#660823
• Bridging the Gap Between Network Science and Network Systems to Identify and Mitigate Cyber Risk: Identify and Mitigate Backdoor Attacks on Graph Neural Networks and on Complex Systems#169445
• Advancing graph neural networks : addressing representation challenges in the vision domain#413324
• An optimized graph neural network approach for robust and explainable IoT intrusion detection against adversarial attacks.#360935