Argot: Generating Adversarial Readable Chinese Texts

IJCAI 2021, download

Zihan Zhang , Mingxuan Liu , Chao Zhang , Yiming Zhang , Zhou Li , Qi Li , Haixin Duan , Donghong Sun .


Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus on analyzing English texts and generating adversarial examples for English texts.
There is no work studying the possibility and effect of the transformation to another language, e.g, Chinese.

In this paper, we analyze the differences between Chinese and English, and explore the methodology to transform the existing English adversarial generation method to Chinese. We propose a novel black-box adversarial Chinese texts generation solution Argot, by utilizing the method for adversarial English samples and several novel methods developed on Chinese characteristics. Argot could effectively and efficiently generate adversarial Chinese texts with good readability. Furthermore, Argot could also automatically generate targeted Chinese adversarial text, achieving a high success rate and ensuring readability of the Chinese.