GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning

arXiv:2406.13499v1 Announce Type: cross
Abstract: Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks. However, these methods can only serve as a defense before poisoning, but cannot repair poisoned GNN. Therefore, there is an urgent need for a method to repair poisoned GNN. In this paper, we address this gap by introducing the novel …

abstract adversarial adversarial attacks application arxiv attacks cs.lg cs.si defense fields gnns graph graph neural networks however machine networks neural networks potential problem robustness serve type unlearning via vulnerable