研究人员开发了新的方法来测试关系深度学习（RDL）模型的对抗性鲁棒性。这些攻击侧重于在遵守模式完整性约束的同时，操纵数据库中的外键引用。该研究引入了七种攻击启发式方法，包括梯度引导变体，这些方法在回归任务上表现出优于随机基线，尽管它们对分类任务的影响不太明显。 AI
影响 这项研究通过识别漏洞并指导开发更好的防御机制，可能有助于构建更鲁棒的关系深度学习系统。
排序理由 该集群包含一篇研究论文，详细介绍了关系深度学习模型的新型对抗性攻击方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.07089v1 Announce Type: new Abstract: Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK…
Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which…