Black-Box Adversarial Attacks on Graph Neural Networks as An Influence Maximization Problem
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 black-box 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 black-box attack strategies. Our experiments verify that the proposed strategies significantly degrade the performance of three popular GNN models and outperform baseline adversarial attack strategies.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization
Recent studies show that well-devised perturbations on graph structures or node features can mislead trained Graph Neural Network (GNN) models. However, these methods often overlook practical assumptions, over-rely on he…
Adversarial AttackGraph Neural NetworkAdversarial Attack on Graph Neural Networks as An Influence Maximization Problem
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, esp…
Adversarial AttackAdversarial Graph Embeddings for Fair Influence Maximization over Social Networks
Influence maximization is a widely studied topic in network science, where the aim is to reach the maximum possible number of nodes, while only targeting a small initial set of individuals. It has critical applications i…
ClusteringFairnessGraph EmbeddingMarketingCan LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs
Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting expressiveness, they also expose new vulnerabilities in graph learning thro…
Graph LearningGRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs
Text-attributed graphs (TAGs), which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to jointly m…