Papers › Certified Robustness of Graph Convolution Networks for Graph Classification under...

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

1 Dec 2020NeurIPS 2020 12archive 2025-07-28

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

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 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 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.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

RobustGraph/RoboGraph officialmentioned in paperpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds,... (arXiv:2312.02708; that paper's own run record: 22 ran (of which 1 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 3 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationGraph Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections