PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing
This work addresses security concerns for GNN deployments by demonstrating practical attacks, though it appears incremental as it builds on existing injection-based methods.
The authors tackled the vulnerability of Graph Neural Networks (GNNs) to structural perturbations by proposing PEANUT, a gradient-free black-box attack that injects virtual nodes to exploit topology-driven message passing, achieving significant performance deterioration across three graph tasks on real-world datasets.
Graph Neural Networks (GNNs) have achieved remarkable performance on tasks involving relational data. However, small perturbations to the graph structure can significantly alter GNN outputs, raising concerns about their robustness in real-world deployments. In this work, we explore the core vulnerability of GNNs which explicitly consume graph topology in the form of the adjacency matrix or Laplacian as a means for message passing, and propose PEANUT, a simple, gradient-free, restricted black-box attack that injects virtual nodes to capitalize on this vulnerability. PEANUT is a injection based attack, which is widely considered to be more practical and realistic scenario than graph modification attacks, where the attacker is able to modify the original graph structure directly. Our method works at the inference phase, making it an evasion attack, and is applicable almost immediately, since it does not involve lengthy iterative optimizations or parameter learning, which add computational and time overhead, or training surrogate models, which are susceptible to failure due to differences in model priors and generalization capabilities. PEANUT also does not require any features on the injected node and consequently demonstrates that GNN performance can be significantly deteriorated even with injected nodes with zeros for features, highlighting the significance of effectively designed connectivity in such attacks. Extensive experiments on real-world datasets across three graph tasks demonstrate the effectiveness of our attack despite its simplicity.