We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs. To poison KGE models, we propose to exploit their inductive abilities which are captured through the relationship patterns like symmetry, inversion and composition in the knowledge graph. Specifically, to degrade the model's prediction confidence on target facts, we propose to improve the model's prediction confidence on a set of decoy facts. Thus, we craft adversarial additions that can improve the model's prediction confidence on decoy facts through different inference patterns. Our experiments demonstrate that the proposed poisoning attacks outperform state-of-art baselines on four KGE models for two publicly available datasets. We also find that the symmetry pattern based attacks generalize across all model-dataset combinations which indicates the sensitivity of KGE models to this pattern.

本论文研究了如何通过数据污染攻击来破坏知识图谱嵌入模型的链接预测任务，提出了一种基于对称、倒置和组合这样的关系模式为基础的对抗性添加方法来提高模型对诱饵事实的预测结果置信度，实验结果表明，这种方法能够针对四个KGE模型和两个公开数据集中的链接预测任务达到比现有技术更好的攻击效果，并且对称模式的攻击方式适用于所有模型和数据集。

通过关系推理模式对知识图谱嵌入进行中毒