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"
}