UAI 2021poster76 citations
Natural language adversarial defense through synonym encoding
Xiaosen Wang, Jin Hao, Yichen Yang, Kun He
Abstract
In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side. Especially, there exists few effective defense method against the successful synonym substitution based attacks that preserve the syntactic structure and semantic information of the original text while fooling the deep learning models. We contribute in this direction and propose a novel adversarial defense method called
BibTeX
@InProceedings{pmlr-v161-wang21a,
title = {Natural language adversarial defense through synonym encoding},
author = {Wang, Xiaosen and Hao, Jin and Yang, Yichen and He, Kun},
booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence},
pages = {823--833},
year = {2021},
editor = {de Campos, Cassio and Maathuis, Marloes H.},
volume = {161},
series = {Proceedings of Machine Learning Research},
month = {27--30 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v161/wang21a/wang21a.pdf},
url = {https://proceedings.mlr.press/v161/wang21a.html},
abstract = {In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side. Especially, there exists few effective defense method against the successful synonym substitution based attacks that preserve the syntactic structure and semantic information of the original text while fooling the deep learning models. We contribute in this direction and propose a novel adversarial defense method called