Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure

arXiv:2404.15065v1 Announce Type: new
Abstract: Graph neural networks are becoming increasingly popular in the field of machine learning due to their unique ability to process data structured in graphs. They have also been applied in safety-critical environments where perturbations inherently occur. However, these perturbations require us to formally verify neural networks before their deployment in safety-critical environments as neural networks are prone to adversarial attacks. While there exists research on the formal verification of neural networks, there is no work …

abstract arxiv cs.ai cs.lg data environments features graph graph neural networks graphs however machine machine learning networks neural networks node popular process safety safety-critical type uncertain unique verification