DeepAI AI Chat
Log In Sign Up

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

09/22/2020
by   Boyuan Feng, et al.
0

Graph neural networks (GNNs) have achieved high performance in analyzing graph-structured data and have been widely deployed in safety-critical areas, such as finance and autonomous driving. However, only a few works have explored GNNs' robustness to adversarial attacks, and their designs are usually limited by the scale of input datasets (i.e., focusing on small graphs with only thousands of nodes). In this work, we propose, SAG, the first scalable adversarial attack method with Alternating Direction Method of Multipliers (ADMM). We first decouple the large-scale graph into several smaller graph partitions and cast the original problem into several subproblems. Then, we propose to solve these subproblems using projected gradient descent on both the graph topology and the node features that lead to considerably lower memory consumption compared to the conventional attack methods. Rigorous experiments further demonstrate that SAG can significantly reduce the computation and memory overhead compared with the state-of-the-art approach, making SAG applicable towards graphs with large size of nodes and edges.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/10/2019

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

Graph neural networks (GNNs) which apply the deep neural networks to gra...
09/08/2020

Adversarial Attack on Large Scale Graph

Recent studies have shown that graph neural networks are vulnerable agai...
10/26/2021

Robustness of Graph Neural Networks at Scale

Graph Neural Networks (GNNs) are increasingly important given their popu...
02/01/2023

A^2Q: Aggregation-Aware Quantization for Graph Neural Networks

As graph data size increases, the vast latency and memory consumption du...
11/15/2022

Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation

Recent studies show that Graph Neural Networks(GNNs) are vulnerable and ...
12/25/2021

Task and Model Agnostic Adversarial Attack on Graph Neural Networks

Graph neural networks (GNNs) have witnessed significant adoption in the ...