Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem

2021/06/21 by Jiaqi Ma, Ma, Jiaqi, Junwei Deng +3 · 1 citation
Computer Science · Materials Science · #Advanced Graph Neural Networks #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.2106.10785

openalex publication_date 2021/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Graph neural networks (GNNs) have attracted increasing interests. With broad deployments of GNNs in real-world applications, there is an urgent need for understanding the robustness of GNNs under adversarial attacks, especially in realistic setups. In this work, we study the problem of attacking GNNs in a restricted and realistic setup, by perturbing the features of a small set of nodes, with no access to model parameters and model predictions. Our formal analysis draws a connection between this type of attacks and an influence maximization problem on the graph. This connection not only enhances our understanding on the problem of adversarial attack on GNNs, but also allows us to propose a group of effective and practical attack strategies. Our experiments verify that the proposed attack strategies significantly degrade the performance of three popular GNN models and outperform baseline adversarial attack strategies.

Cited by

• Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations

Related

• GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization
• Generating Adversarial Examples with Graph Neural Networks
• Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
• Task and Model Agnostic Adversarial Attack on Graph Neural Networks