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

TL;DR

This paper introduces SAG, a scalable adversarial attack method on large graph neural networks using ADMM, which reduces memory and computation costs, enabling attacks on large-scale graphs.

Contribution

SAG is the first scalable adversarial attack method on GNNs that leverages ADMM to handle large graphs efficiently.

Findings

SAG significantly reduces memory consumption compared to existing methods.

SAG decreases computational overhead, enabling attacks on large graphs.

Experiments show SAG's effectiveness on large-scale graph datasets.

Abstract

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.