← Search

Hanyuan Huang

2 accepted papers

2025

Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience

AAAI 2025technical

End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing critic…

Cited by 0SourcePDFScholar
2024

Towards Inductive Robustness: Distilling and Fostering Wave-Induced Resonance in Transductive GCNs against Graph Adversarial Attacks

AAAI 2024technical

Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defending against such attacks inherit the transductive limitations of graph convolut…

Cited by 5SourcePDFScholar