VGFL-SA：基于对比学习的纵向图联邦学习结构攻击
VGFL-SA: Vertical Graph Federated Learning Structure Attack Based on Contrastive Learning
AI总结：
针对纵向图联邦学习中客户端节点无标签导致现有攻击受限的问题，提出VGFL-SA，利用对比学习和邻接矩阵梯度修改本地图结构，实验证明其攻击有效且可迁移。
摘要：
图神经网络（GNN）因其从图数据中学习表示的能力而受到关注。由于隐私问题和利益冲突阻碍客户端彼此直接共享图数据，纵向图联邦学习（VGFL）框架得到了发展。近期研究表明，VGFL容易受到会降低性能的对抗攻击。然而，在VGFL领域，客户端节点通常没有标签是一个普遍问题。因此，依赖标签信息可用性来获取梯度的现有攻击在适用性上天然受到限制。这一局限使其无法部署到实际的真实环境中。为解决上述问题，我们提出了一种针对VGFL的新型图对抗攻击，称为VGFL-SA，通过在不使用标签的情况下修改本地客户端结构来降低VGFL性能。具体而言，VGFL-SA使用对比学习方法，在本地客户端接受训练之前完成攻击。VGFL-SA首先访问被投毒客户端的图结构和节点特征信息，并通过基于节点度的边增强和特征洗牌增强生成对比视图。随后，VGFL-SA使用共享图编码器获得每个视图的嵌入，并通过对比函数获得邻接矩阵的梯度。最后，使用梯度修改规则生成扰动边。我们通过在真实世界数据集上执行节点分类任务验证了VGFL-SA的性能，结果表明VGFL-SA取得了良好的攻击效果和可迁移性。
英文摘要：
Graph Neural Networks (GNNs) have gained attention for their ability to learn representations from graph data. Due to privacy concerns and conflicts of interest that prevent clients from directly sharing graph data with one another, Vertical Graph Federated Learning (VGFL) frameworks have been developed. Recent studies have shown that VGFL is vulnerable to adversarial attacks that degrade performance. However, it is a common problem that client nodes are often unlabeled in the realm of VGFL. Consequently, the existing attacks, which rely on the availability of labeling information to obtain gradients, are inherently constrained in their applicability. This limitation precludes their deployment in practical, real-world environments. To address the above problems, we propose a novel graph adversarial attack against VGFL, referred to as VGFL-SA, to degrade the performance of VGFL by modifying the local clients structure without using labels. Specifically, VGFL-SA uses a contrastive learning method to complete the attack before the local clients are trained. VGFL-SA first accesses the graph structure and node feature information of the poisoned clients, and generates the contrastive views by node-degree-based edge augmentation and feature shuffling augmentation. Then, VGFL-SA uses the shared graph encoder to get the embedding of each view, and the gradients of the adjacency matrices are obtained by the contrastive function. Finally, perturbed edges are generated using gradient modification rules. We validated the performance of VGFL-SA by performing a node classification task on real-world datasets, and the results show that VGFL-SA achieves good attack effectiveness and transferability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
