all InfoSec news
Adversarially Robust Neural Architecture Search for Graph Neural Networks. (arXiv:2304.04168v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Graph Neural Networks (GNNs) obtain tremendous success in modeling relational
data. Still, they are prone to adversarial attacks, which are massive threats
to applying GNNs to risk-sensitive domains. Existing defensive methods neither
guarantee performance facing new data/tasks or adversarial attacks nor provide
insights to understand GNN robustness from an architectural perspective. Neural
Architecture Search (NAS) has the potential to solve this problem by automating
GNN architecture designs. Nevertheless, current graph NAS approaches lack
robust design and are vulnerable to adversarial …
adversarial adversarial attacks architecture attacks challenges current data defensive design domains guarantee insights modeling nas networks neural networks novel performance perspective problem risk robustness search threats understand vulnerable