@inproceedings{bhardwaj-etal-2021-poisoning,
    title = "Poisoning Knowledge Graph Embeddings via Relation Inference Patterns",
    author = "Bhardwaj, Peru  and
      Kelleher, John  and
      Costabello, Luca  and
      O{'}Sullivan, Declan",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2021.acl-long.147/",
    doi = "10.18653/v1/2021.acl-long.147",
    pages = "1875--1888",
    abstract = "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."
}