DeepAI AI Chat
Log In Sign Up

Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces

by   Linyang Li, et al.

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 '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.


page 1

page 2

page 3

page 4


AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text

Adversarial examples are vital to expose the vulnerability of machine le...

Classical Chinese Sentence Segmentation for Tomb Biographies of Tang Dynasty

Tomb biographies of the Tang dynasty provide invaluable information abou...

CycleGAN: a Master of Steganography

CycleGAN is one of the latest successful approaches to learn a correspon...

How Far Are We from Real Synonym Substitution Attacks?

In this paper, we explore the following question: how far are we from re...

Exploiting Language Model for Efficient Linguistic Steganalysis

Recent advances in linguistic steganalysis have successively applied CNN...

PaCaNet: A Study on CycleGAN with Transfer Learning for Diversifying Fused Chinese Painting and Calligraphy

AI-Generated Content (AIGC) has recently gained a surge in popularity, p...