On Stealing Graph Neural Network Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915614647386112 |
|---|---|
| author | Podhajski, Marcin Dubiński, Jan Boenisch, Franziska Dziedzic, Adam Pręgowska, Agnieszka Michalak, Tomasz P. |
| author_facet | Podhajski, Marcin Dubiński, Jan Boenisch, Franziska Dziedzic, Adam Pręgowska, Agnieszka Michalak, Tomasz P. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On Stealing Graph Neural Network Models Podhajski, Marcin Dubiński, Jan Boenisch, Franziska Dziedzic, Adam Pręgowska, Agnieszka Michalak, Tomasz P. Machine Learning Cryptography and Security 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. |
| title | On Stealing Graph Neural Network Models |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2511.07170 |