Attacking Graph Foundation Models Through Their Shared Representation
Researchers have identified a novel attack surface in graph foundation models: the alignment layer that maps diverse graph inputs into a shared representation. They demonstrate that targeted perturbations in this representation space can severely degrade model performance, with some models—such as OpenGraph—being particularly vulnerable. Additionally, input-space attacks that modify edges, features, or text can eliminate at least half of correct predictions in three out of six tested models.
Why it matters: This work exposes a previously unexamined vulnerability in graph foundation models that can be exploited at inference time without access to training data, raising new security concerns for real-world deployments.
Full story at: arXiv AI/ML ↗