GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

arXiv:2605.12827v1 Announce Type: cross Abstract: Graph neural networks (GNNs) deployed as cloud services can be \emph{stolen} through \emph{model-extraction attacks}, which train a surrogate from query responses to reproduce the target's behaviour, and a growing line of ownership defenses tries to...