Generating Textual Adversaries with Minimal Perturbation

Xingyi Zhao, Lu Zhang, Depeng Xu, Shuhan Yuan


Abstract
Many word-level adversarial attack approaches for textual data have been proposed in recent studies. However, due to the massive search space consisting of combinations of candidate words, the existing approaches face the problem of preserving the semantics of texts when crafting adversarial counterparts. In this paper, we develop a novel attack strategy to find adversarial texts with high similarity to the original texts while introducing minimal perturbation. The rationale is that we expect the adversarial texts with small perturbation can better preserve the semantic meaning of original texts. Experiments show that, compared with state-of-the-art attack approaches, our approach achieves higher success rates and lower perturbation rates in four benchmark datasets.
Anthology ID:
2022.findings-emnlp.337
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4599–4606
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.337
DOI:
10.18653/v1/2022.findings-emnlp.337
Bibkey:
Cite (ACL):
Xingyi Zhao, Lu Zhang, Depeng Xu, and Shuhan Yuan. 2022. Generating Textual Adversaries with Minimal Perturbation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4599–4606, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Generating Textual Adversaries with Minimal Perturbation (Zhao et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.337.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.337.mp4