# Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks Source: [Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks]() Collection index: [llms.txt]() Data updated: 2025-10-26T03:40:43.406Z Authors: Marcin Podhajski, Jan Dubi\\'nski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pregowska, Tomasz P. Michalak Published: 2024-05-20T18:01:15.000Z ## Abstract 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 on predefined graph structures, are becoming increasingly important in a wide range of applications. As such these networks become attractive targets for model-stealing attacks where an adversary seeks to replicate the functionality of the targeted network. Significant efforts have been devoted to developing model-stealing attacks that extract models trained on images and texts. However, little attention has been given to stealing GNNs trained on graph data. This paper identifies a new method of performing unsupervised model-stealing attacks against inductive GNNs, utilizing graph contrastive learning and spectral graph augmentations to efficiently extract information from the targeted model. The new type of attack is thoroughly evaluated on six datasets and the results show that our approach outperforms the current state-of-the-art by Shen et al. (2021). In particular, our attack surpasses the baseline across all benchmarks, attaining superior fidelity and downstream accuracy of the stolen model while necessitating fewer queries directed toward the target model. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Graph Model Stealing on HIV](): Graph Model Stealing; HIV; AUC: 62.69. - [Node Classification on PubMed (AUC, Fidelity, Rank Corr.)](): Node Classification; Pubmed; AUC: 85.93. - [Model Stealing on NCI1](): Model Stealing; NCI1; AUC: 75.93. - [Model Stealing on NCI109](): Model Stealing; NCI109; AUC: 73.94. - [Graph Model Stealing on Tox21](): Graph Model Stealing; Tox21; AUC: 74.47. - [Graph Model Stealing on BACE](): Graph Model Stealing; BACE; AUC: 69.94. - [Model Stealing on AIDS](): Model Stealing; AIDS; AUC: 89.34. - [Model Stealing on Mutagenicity](): Model Stealing; Mutagenicity; AUC: 81.31. - [Node classification on ogb-arxiv (AUC, Fidelity, Rank Corr.)](): Node Classification; OGB-arxiv; AUC: 86.95. - [Graph Classification Model Stealing on Mutagenicity](): Graph Classification Model Stealing; Mutagenicity; AUC: 79.69. ## Original sources and implementation [Original paper]() [PDF]()