@Article{jai.2021.016305,
AUTHOR = {Huixuan Xu, Chunlai Du, Yanhui Guo, Zhijian Cui, Haibo Bai},
TITLE = {A Generation Method of Letter-Level Adversarial Samples},
JOURNAL = {Journal on Artificial Intelligence},
VOLUME = {3},
YEAR = {2021},
NUMBER = {2},
PAGES = {45--53},
URL = {http://www.techscience.com/jai/v3n2/42529},
ISSN = {2579-003X},
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.},
DOI = {10.32604/jai.2021.016305}
}