2 papers
cs.LG2025
Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
Junyuan Fang, Han Yang, Haixian Wen +3
Graph neural networks have been widely utilized to solve graph-related tasks because of their strong learning power in utilizing the local information of neighbors. However, recent…
cs.LG2025
Mitigating the Structural Bias in Graph Adversarial Defenses
Junyuan Fang, Huimin Liu, Han Yang +3
In recent years, graph neural networks (GNNs) have shown great potential in addressing various graph structure-related downstream tasks. However, recent studies have found that cur…