English

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces

Computation and Language 2021-01-01 v1

Abstract

Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in Chinese, such methods are not applicable since words in Chinese require segmentations first. In this paper, we propose a pre-train language model as the substitutes generator using sentence-pieces to craft adversarial examples in Chinese. The substitutions in the generated adversarial examples are not characters or words but \textit{'pieces'}, which are more natural to Chinese readers. Experiments results show that the generated adversarial samples can mislead strong target models and remain fluent and semantically preserved.

Keywords

Cite

@article{arxiv.2012.14769,
  title  = {Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces},
  author = {Linyang Li and Yunfan Shao and Demin Song and Xipeng Qiu and Xuanjing Huang},
  journal= {arXiv preprint arXiv:2012.14769},
  year   = {2021}
}

Comments

pre-print

R2 v1 2026-06-23T21:33:28.559Z