EMNLP 2021main17 citations

Adversarial Attack against Cross-lingual Knowledge Graph Alignment

Zeru Zhang, Zijie Zhang, Yang Zhou, Lingfei Wu, Sixing Wu, Xiaoying Han, Dejing Dou, Tianshi Che

Abstract

Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks. However, there is still a paucity of vulnerability analyses of cross-lingual entity alignment under adversarial attacks. This paper proposes an adversarial attack model with two novel attack techniques to perturb the KG structure and degrade the quality of deep cross-lingual entity alignment. First, an entity density maximization method is employed to hide the attacked entities in dense regions in two KGs, such that the derived perturbations are unnoticeable. Second, an attack signal amplification method is developed to reduce the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness.

BibTeX
@inproceedings{zhang-etal-2021-adversarial-attack,
    title = "Adversarial Attack against Cross-lingual Knowledge Graph Alignment",
    author = "Zhang, Zeru  and
      Zhang, Zijie  and
      Zhou, Yang  and
      Wu, Lingfei  and
      Wu, Sixing  and
      Han, Xiaoying  and
      Dou, Dejing  and
      Che, Tianshi  and
      Yan, Da",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-main.432/",
    doi = "10.18653/v1/2021.emnlp-main.432",
    pages = "5320--5337"
}
Adversarial Attack against Cross-lingual Knowledge Graph Alignment · EMNLP 2021