Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing

ArXi:2510.18591v2 Announce Type: replace Graph neural networks (GNNs) are the predominant architecture for learning over graphs. As with any machine learning model, an important issue is the detection of attacks, where an adversary can change the output with a small perturbation of the input. Techniques for solving the adversarial robustness problem - determining whether an attack exists - were originally developed for image classification.