Open Access
ARTICLE
A Generation Method of Letter-Level Adversarial Samples
Huixuan Xu1, Chunlai Du1, Yanhui Guo2,*, Zhijian Cui1, Haibo Bai1
1 School of Information Science and Technology, North China University of Technology, Beijing, 100144, China
2 Department of Computer Science, University of Illinois Springfield, Springfield, USA
* Corresponding Author: Yanhui Guo. Email:
Journal on Artificial Intelligence 2021, 3(2), 45-53. https://doi.org/10.32604/jai.2021.016305
Received 29 December 2020; Accepted 22 March 2021; Issue published 08 May 2021
Abstract
In recent years, with the rapid development of natural language
processing, the security issues related to it have attracted more and more
attention. Character perturbation is a common security problem. It can try to
completely modify the input classification judgment of the target program
without people’s attention by adding, deleting, or replacing several characters,
which can reduce the effectiveness of the classifier. Although the current
research has provided various methods of perturbation attacks on characters, the
success rate of some methods is still not ideal. This paper mainly studies the
sample generation of optimal perturbation characters and proposes a characterlevel text adversarial sample generation method. The goal is to use this method
to achieve the best effect on character perturbation. After sentiment classification
experiments, this model has a higher perturbation success rate on the IMDB
dataset, which proves the effectiveness and rationality of this method for text
perturbation and provides a reference for future research work.
Keywords
Cite This Article
H. Xu, C. Du, Y. Guo, Z. Cui and H. Bai, "A generation method of letter-level adversarial samples,"
Journal on Artificial Intelligence, vol. 3, no.2, pp. 45–53, 2021. https://doi.org/10.32604/jai.2021.016305