Robustness of Graph Neural Networks at Scale

10/26/2021
by   Simon Geisler, et al.
0

Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications. Yet, existing studies of their vulnerability to adversarial attacks rely on relatively small graphs. We address this gap and study how to attack and defend GNNs at scale. We propose two sparsity-aware first-order optimization attacks that maintain an efficient representation despite optimizing over a number of parameters which is quadratic in the number of nodes. We show that common surrogate losses are not well-suited for global attacks on GNNs. Our alternatives can double the attack strength. Moreover, to improve GNNs' reliability we design a robust aggregation function, Soft Median, resulting in an effective defense at all scales. We evaluate our attacks and defense with standard GNNs on graphs more than 100 times larger compared to previous work. We even scale one order of magnitude further by extending our techniques to a scalable GNN.

READ FULL TEXT
06/12/2021

TDGIA:Effective Injection Attacks on Graph Neural Networks

Graph Neural Networks (GNNs) have achieved promising performance in vari...
06/21/2021

Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem

Graph neural networks (GNNs) have attracted increasing interests. With b...
09/28/2020

RoGAT: a robust GNN combined revised GAT with adjusted graphs

Graph Neural Networks(GNNs) are useful deep learning models to deal with...
09/22/2020

Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks

With the increasing popularity of graph-based learning, graph neural net...
03/18/2022

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations

Recent progress in Graph Neural Networks (GNNs) for modeling atomic simu...
06/14/2021

Improving Robustness of Graph Neural Networks with Heterophily-Inspired Designs

Recent studies have exposed that many graph neural networks (GNNs) are s...
09/22/2020

Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers

Graph neural networks (GNNs) have achieved high performance in analyzing...