Graph Structural Attack by Perturbing Spectral Distance. (arXiv:2111.00684v3 [cs.LG] UPDATED)

Graph Convolutional Networks (GCNs) have fueled a surge of research interest
due to their encouraging performance on graph learning tasks, but they are also
shown vulnerability to adversarial attacks. In this paper, an effective graph
structural attack is investigated to disrupt graph spectral filters in the
Fourier domain, which are the theoretical foundation of GCNs. We define the
notion of spectral distance based on the eigenvalues of graph Laplacian to
measure the disruption of spectral filters. We realize the attack …

attack spectral