all InfoSec news
Robust Mid-Pass Filtering Graph Convolutional Networks. (arXiv:2302.08048v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Graph convolutional networks (GCNs) are currently the most promising paradigm
for dealing with graph-structure data, while recent studies have also shown
that GCNs are vulnerable to adversarial attacks. Thus developing GCN models
that are robust to such attacks become a hot research topic. However, the
structural purification learning-based or robustness constraints-based defense
GCN methods are usually designed for specific data or attacks, and introduce
additional objective that is not for classification. Extra training overhead is
also required in their design. …
adversarial adversarial attacks attacks classification constraints data defense hot networks paradigm research robustness studies vulnerable