摘要
图神经网络在半监督节点分类任务中取得了显著的性能.研究表明,图神经网络容易受到干扰,因此目前已有研究涉及图神经网络的对抗鲁棒性.然而,基于梯度的攻击不能保证最优的扰动.提出了一种基于梯度和结构的对抗性攻击方法,增强了基于梯度的扰动.该方法首先利用训练损失的一阶优化生成候选扰动集,然后对候选集进行相似性评估,根据评估结果排序并选择固定预算的修改以实现攻击.通过在5个数据集上进行半监督节点分类任务来评估所提出的攻击方法.实验结果表明,在仅执行少量扰动的情况下,节点分类精度显著下降,明显优于现有攻击方法.
Graph neural networks have achieved remarkable performance in semi-supervised node classification tasks.Relevant research has shown that graph neural networks are susceptible to perturbations,and there is research studying the adversarial robustness of graph neural networks.However,gradient-based attacks cannot guarantee optimal perturbation.Therefore,an adversarial attack method based on gradient and structure is proposed to enhance the gradient-based perturbation.The method first generates candidate perturbation sets by using first-order optimization of training losses,and then it evaluates the similarity of the candidate sets.Finally,it ranks them according to the evaluation results and selects a fixed-budget modification to achieve the attack.The proposed attack method is evaluated by performing a semisupervised node classification task on five datasets.Experimental results show that the node classification accuracy decreases significantly when only a small number of perturbations are performed,which indicates that the proposed method significantly outperforms the existing attack methods.
作者
李凝书
关东海
袁伟伟
LI Ning-Shu;GUAN Dong-Hai;YUAN Wei-Wei(College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)
出处
《计算机系统应用》
2023年第7期276-283,共8页
Computer Systems & Applications
基金
国防基础科研计划(JCKY2020204C009)。
关键词
图神经网络
节点分类
对抗性攻击
梯度攻击
graph neural network(GNN)
node classification
adversarial attacks
gradient attacks
