Can I read GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization on EtoBox?

GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization by Yang, Xiaodong; Li, Xiaoting; Chen, Huiyuan; Cai, Yiwei is a scholarly article available to read on EtoBox.

What is GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization about?

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 heuristics, or separate vital attack components. In response, we present GAIM, an integrated adversarial attack method conducted on a node feature basis while considering the strict black-box setting. Specifically, we define an adversarial influence function to theoretically assess the adversarial impact of node perturbations, thereby reframing the GNN attack problem into the adversarial influence maximization problem. In our approach, we unify the selection of the target node and the construction of feature perturbations into a single optimization problem, ensuring a unique and consistent feature perturbation for each target node. We leverage a surrogate model to transform this problem into a solvable linear programming task, streamlining the optimization process. Moreover, we extend our method to accommodate label-oriented attacks, broadening its applicability. Thorough evaluations on five benchmark datasets across three popular models underscore the effectiveness o

Author

Yang, Xiaodong; Li, Xiaoting; Chen, Huiyuan; Cai, Yiwei

Published

2024

Language

EN