计算机与数字工程2024，Vol.52Issue(10)：3003-3008,6.DOI:10.3969/j.issn.1672-9722.2024.10.026
针对图神经网络的单节点扰动攻击
Single Node Adversarial Attack Against Graph Neural Network
摘要
Abstract
Graph neural networks(GNNs)have shown excellent performance in a variety of graph-related applications.Re-cent studies show that GNN models are vulnerable to carefully construct adversarial perturbations,resulting in degraded model per-formance.Most of the previous research on graph adversarial attacks focus on modifying the graph structure,which will change the important topology properties of the graph.Indirect adversarial attacks on graph data are studied,and a single node adversarial at-tack(SNAA)based on reinforcement learning to modify the node features in graphs is proposed.The attack is set in a black-box scenario,where only a limited number of black-box queries can be performed on the test data,and the attack budget is strictly limit-ed to ensure that the attack is imperceptible.Experiments on multiple datasets show that SNAA is effective against various GNN models.关键词
图神经网络/图对抗攻击/强化学习/对抗样本Key words
graph neural network/graph adversarial attack/reinforcement learning/adversarial example分类
信息技术与安全科学引用本文复制引用
李鹏辉,翟正利,冯舒..针对图神经网络的单节点扰动攻击[J].计算机与数字工程,2024,52(10):3003-3008,6.基金项目
国家自然科学基金项目(编号:61502262)资助. （编号:61502262）
