Poisoning Knowledge Graph Embeddings via Relation Inference Patterns

Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O’Sullivan


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.
Anthology ID:
2021.acl-long.147
Volume:
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:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1875–1888
Language:
URL:
https://aclanthology.org/2021.acl-long.147
DOI:
10.18653/v1/2021.acl-long.147
Bibkey:
Cite (ACL):
Peru Bhardwaj, John Kelleher, Luca Costabello, and Declan O’Sullivan. 2021. Poisoning Knowledge Graph Embeddings via Relation Inference Patterns. In 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), pages 1875–1888, Online. Association for Computational Linguistics.
Cite (Informal):
Poisoning Knowledge Graph Embeddings via Relation Inference Patterns (Bhardwaj et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.147.pdf
Video:
 https://aclanthology.org/2021.acl-long.147.mp4
Code
 perubhardwaj/inferenceattack
Data
FB15k-237