有向图神经网络能否具备对抗鲁棒性？
Harnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning
AI总结：
本文首次研究有向图 GNN 的对抗鲁棒性，提出真实攻击设定及通用高效的消息传递插件框架，结合现有防御实现最先进鲁棒性能。
摘要：
现有关于鲁棒图神经网络（GNN）的研究未能认识到有向图在提供网络内在结构丰富信息方面的重要性。本工作首次考察了有向图场景下 GNN 的鲁棒性，旨在利用有向图所提供的深刻信任含义来增强 GNN 的鲁棒性与恢复能力。我们的研究揭示，现有有向 GNN 并不具备对抗鲁棒性。为实现目标，我们引入了一种新的、现实的有向图攻击设定，并提出一个创新、通用且高效的消息传递框架，将其作为插件层以显著提升 GNN 的鲁棒性。该框架与现有防御策略结合后，可取得出色的干净准确率和最先进的鲁棒性能，并针对迁移攻击与自适应攻击提供更强防御。本研究的发现为这一关键研究领域揭示了一个新颖且有前景的方向。论文被接收后，代码将公开发布。
英文摘要：
Existing research on robust Graph Neural Networks (GNNs) focuses predominantly on undirected graphs, overlooking the trustworthiness inherent in the link directions of directed graphs. In this work, we analyze the limitations of current approaches from both the attack and defense perspectives and redefine the robustness of GNNs in directed graphs. From the attack side, we introduce a more realistic directed graph attack setting that addresses the shortcomings of existing attacks. From the defense side, we propose a simple yet effective message-passing framework that serves as a plug-in layer to strengthen GNN robustness while avoiding a false sense of robustness. Our findings show that the trust signals encoded in directed graphs can be harnessed to substantially improve the robustness of GNNs. When combined with existing defense strategies, the framework achieves state-of-the-art robust performance alongside strong clean accuracy against both transfer and adaptive attacks. These results point to a novel and promising direction for strengthening the robustness of graph deep learning.
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。
