Exact Verification of Graph Neural Networks with Incremental Constraint Solving

ArXi:2508.09320v3 Announce Type: replace-cross Graph neural networks (GNNs) are increasingly often employed in high-stakes applications, such as fraud detection or healthcare, but are susceptible to adversarial attacks. A number of techniques have been proposed to provide adversarial robustness guarantees, but for commonly used aggregation functions in message-passing GNNs is lacking.