GrOVe: Ownership Verification of Graph Neural Networks using Embeddings
Graph neural networks (GNNs) have emerged as a state-of-the-art approach to model and draw inferences from large scale graph-structured data in various application settings such as social networking. The primary goal of a GNN is to learn an embedding for each graph node in a dataset that encodes bot...
Saved in:
Main Authors | , , |
---|---|
Format | Journal Article |
Language | English |
Published |
17.04.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Graph neural networks (GNNs) have emerged as a state-of-the-art approach to
model and draw inferences from large scale graph-structured data in various
application settings such as social networking. The primary goal of a GNN is to
learn an embedding for each graph node in a dataset that encodes both the node
features and the local graph structure around the node. Embeddings generated by
a GNN for a graph node are unique to that GNN. Prior work has shown that GNNs
are prone to model extraction attacks. Model extraction attacks and defenses
have been explored extensively in other non-graph settings. While detecting or
preventing model extraction appears to be difficult, deterring them via
effective ownership verification techniques offer a potential defense. In
non-graph settings, fingerprinting models, or the data used to build them, have
shown to be a promising approach toward ownership verification. We present
GrOVe, a state-of-the-art GNN model fingerprinting scheme that, given a target
model and a suspect model, can reliably determine if the suspect model was
trained independently of the target model or if it is a surrogate of the target
model obtained via model extraction. We show that GrOVe can distinguish between
surrogate and independent models even when the independent model uses the same
training dataset and architecture as the original target model. Using six
benchmark datasets and three model architectures, we show that consistently
achieves low false-positive and false-negative rates. We demonstrate that is
robust against known fingerprint evasion techniques while remaining
computationally efficient. |
---|---|
DOI: | 10.48550/arxiv.2304.08566 |