Enhance Robustness of Language Models against Variation Attack through Graph Integration

Zi Xiong, Lizhi Qing, Yangyang Kang, Jiawei Liu, Hongsong Li, Changlong Sun, Xiaozhong Liu, Wei Lu


Abstract
The widespread use of pre-trained language models (PLMs) in natural language processing (NLP) has greatly improved performance outcomes. However, these models’ vulnerability to adversarial attacks (e.g., camouflaged hints from drug dealers), particularly in the Chinese language with its rich character diversity/variation and complex structures, hatches vital apprehension. In this study, we propose a novel method, CHinese vAriatioN Graph Enhancement (CHANGE), to increase the robustness of PLMs against character variation attacks in Chinese content. CHANGE presents a novel approach to incorporate a Chinese character variation graph into the PLMs. Through designing different supplementary tasks utilizing the graph structure, CHANGE essentially enhances PLMs’ interpretation of adversarially manipulated text. Experiments conducted in a multitude of NLP tasks show that CHANGE outperforms current language models in combating against adversarial attacks and serves as a valuable contribution to robust language model research. Moreover, these findings highlight the substantial potential of graph-guided pre-training strategies for real-world applications.
Anthology ID:
2024.lrec-main.520
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
5866–5877
Language:
URL:
https://aclanthology.org/2024.lrec-main.520
DOI:
Bibkey:
Cite (ACL):
Zi Xiong, Lizhi Qing, Yangyang Kang, Jiawei Liu, Hongsong Li, Changlong Sun, Xiaozhong Liu, and Wei Lu. 2024. Enhance Robustness of Language Models against Variation Attack through Graph Integration. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5866–5877, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Enhance Robustness of Language Models against Variation Attack through Graph Integration (Xiong et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.520.pdf