Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks

Ao Wang, Xinghao Yang, Chen Li, Bao-di Liu, Weifeng Liu


Abstract
Adversarial textual examples reveal the vulnerability of natural language processing (NLP) models. Most existing text attack methods are designed for English text, while the robust implementation of the second popular language, i.e., Chinese with 1 billion users, is greatly underestimated. Although several Chinese attack methods have been presented, they either directly transfer from English attacks or adopt simple greedy search to optimize the attack priority, usually leading to unnatural sentences. To address these issues, we propose an adaptive Immune-based Sound-Shape Code (ISSC) algorithm for adversarial Chinese text attacks. Firstly, we leverage the Sound-Shape code to generate natural substitutions, which comprehensively integrate multiple Chinese features. Secondly, we employ adaptive immune algorithm (IA) to determine the replacement order, which can reduce the duplication of population to improve the search ability. Extensive experimental results validate the superiority of our ISSC in producing high-quality Chinese adversarial texts. Our code and data can be found in https://github.com/nohuma/chinese-attack-issc.
Anthology ID:
2024.emnlp-main.262
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4553–4565
Language:
URL:
https://aclanthology.org/2024.emnlp-main.262/
DOI:
10.18653/v1/2024.emnlp-main.262
Bibkey:
Cite (ACL):
Ao Wang, Xinghao Yang, Chen Li, Bao-di Liu, and Weifeng Liu. 2024. Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4553–4565, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks (Wang et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.262.pdf
Software:
 2024.emnlp-main.262.software.zip
Data:
 2024.emnlp-main.262.data.zip