研究人员开发了GJDNet，一个旨在增强图神经网络（GNN）对抗对抗性攻击鲁棒性的新框架。这些攻击利用图连通性中的结构反转，导致不匹配并破坏GNN性能。GJDNet通过解耦节点表示和决策空间来解决这个问题，隔离扰动的影响并确保更清晰的决策边界。该框架利用特征驱动的软结构解耦和球形决策边界机制，以提高各种图类型的准确性和稳定性。 AI
影响 增强了GNN的安全性，可能使其在敏感应用中更可靠地部署。
排序理由 该集群包含一篇详细介绍提高GNN鲁棒性新方法的论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.01560v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and assortative edges in disassortative graphs. This struc…
Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and assortative edges in disassortative graphs. This structural inversion creates structure-feature mismatch…