Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing

09/12/2020
by   Zhidong Gao, et al.
26

Graph classification has practical applications in diverse fields. Recent studies show that graph-based machine learning models are especially vulnerable to adversarial perturbations due to the non i.i.d nature of graph data. By adding or deleting a small number of edges in the graph, adversaries could greatly change the graph label predicted by a graph classification model. In this work, we propose to build a smoothed graph classification model with certified robustness guarantee. We have proven that the resulting graph classification model would output the same prediction for a graph under l_0 bounded adversarial perturbation. We also evaluate the effectiveness of our approach under graph convolutional network (GCN) based multi-class graph classification model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/11/2020

I-GCN: Robust Graph Convolutional Network via Influence Mechanism

Deep learning models for graphs, especially Graph Convolutional Networks...
research
06/10/2019

Attacking Graph Convolutional Networks via Rewiring

Graph Neural Networks (GNNs) have boosted the performance of many graph ...
research
02/16/2023

Robust Mid-Pass Filtering Graph Convolutional Networks

Graph convolutional networks (GCNs) are currently the most promising par...
research
06/20/2023

Structure-Aware Robustness Certificates for Graph Classification

Certifying the robustness of a graph-based machine learning model poses ...
research
02/24/2021

Graphfool: Targeted Label Adversarial Attack on Graph Embedding

Deep learning is effective in graph analysis. It is widely applied in ma...
research
10/12/2017

Graph Convolutional Networks for Classification with a Structured Label Space

It is a usual practice to ignore any structural information underlying c...
research
03/12/2020

Topological Effects on Attacks Against Vertex Classification

Vertex classification is vulnerable to perturbations of both graph topol...

Please sign up or login with your details

Forgot password? Click here to reset