Abstract | ||
---|---|---|
Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph.Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering and recommendation, KGE has gained significant attention recently. Despite its effectiveness in a benign environment, KGEu0027 robustness to adversarial attacks is not well-studied. Existing attack methods on graph data cannot be directly applied to attack the embeddings of knowledge graph due to its heterogeneity. To fill this gap, we propose a collection of data poisoning attack strategies, which can effectively manipulate the plausibility of arbitrary targeted facts in a knowledge graph by adding or deleting facts on the graph. The effectiveness and efficiency of the proposed attack strategies are verified by extensive evaluations on two widely-used benchmarks. |
Year | DOI | Venue |
---|---|---|
2019 | 10.24963/ijcai.2019/674 | arXiv: Learning |
DocType | Volume | Citations |
Journal | abs/1904.12052 | 3 |
PageRank | References | Authors |
0.37 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hengtong Zhang | 1 | 20 | 4.65 |
Tianhang Zheng | 2 | 7 | 2.17 |
Jing Gao | 3 | 2723 | 131.05 |
Chenglin Miao | 4 | 91 | 7.44 |
lu su | 5 | 1118 | 66.61 |
yaliang li | 6 | 629 | 50.87 |
Kui Ren | 7 | 7927 | 355.27 |