Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks

Part of Advances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020)

Bibtex »Paper »Supplemental »

Bibtek download is not availble in the pre-proceeding


Authors

Hongwei Jin, Zhan Shi, Venkata Jaya Shankar Ashish Peruri, Xinhua Zhang

Abstract

<p>Graph convolution networks (GCNs) have become effective models for graph classification. Similar to many deep networks, GCNs are vulnerable to adversarial attacks on graph topology and node attributes. Recently, a number of effective attack and defense algorithms have been developed, but certificates of robustness against \emph{topological perturbations} are currently available only for PageRank and label/feature propagation, while none has been designed for GCNs. We propose the first algorithm for certifying the robustness of GCNs to topological attacks in the application of \emph{graph classification}. Our method is based on Lagrange dualization and convex envelope, which result in tight approximation bounds that are efficiently computable by dynamic programming. When used in conjunction with robust training, it allows an increased number of graphs to be certified as robust.</p>