Task and Model Agnostic Adversarial Attack on Graph Neural Networks. (arXiv:2112.13267v2 [cs.LG] UPDATED)

Adversarial attacks on Graph Neural Networks (GNNs) reveal their security
vulnerabilities, limiting their adoption in safety-critical applications.
However, existing attack strategies rely on the knowledge of either the GNN
model being used or the predictive task being attacked. Is this knowledge
necessary? For example, a graph may be used for multiple downstream tasks
unknown to a practical attacker. It is thus important to test the vulnerability
of GNNs to adversarial perturbations in a model and task agnostic setting. In
this …

adversarial attack networks neural networks task