@inproceedings{li-etal-2021-searching,
title = "Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution",
author = "Li, Zongyi and
Xu, Jianhan and
Zeng, Jiehang and
Li, Linyang and
Zheng, Xiaoqing and
Zhang, Qi and
Chang, Kai-Wei and
Hsieh, Cho-Jui",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.251",
doi = "10.18653/v1/2021.emnlp-main.251",
pages = "3137--3147",
abstract = "Recent studies have shown that deep neural network-based models are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks, and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin. We hope this study could provide useful clues for future research on text adversarial defense. Codes are available at \url{https://github.com/RockyLzy/TextDefender}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-searching">
<titleInfo>
<title>Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zongyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianhan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiehang</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cho-Jui</namePart>
<namePart type="family">Hsieh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent studies have shown that deep neural network-based models are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks, and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin. We hope this study could provide useful clues for future research on text adversarial defense. Codes are available at https://github.com/RockyLzy/TextDefender.</abstract>
<identifier type="citekey">li-etal-2021-searching</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.251</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.251</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3137</start>
<end>3147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution
%A Li, Zongyi
%A Xu, Jianhan
%A Zeng, Jiehang
%A Li, Linyang
%A Zheng, Xiaoqing
%A Zhang, Qi
%A Chang, Kai-Wei
%A Hsieh, Cho-Jui
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F li-etal-2021-searching
%X Recent studies have shown that deep neural network-based models are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks, and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin. We hope this study could provide useful clues for future research on text adversarial defense. Codes are available at https://github.com/RockyLzy/TextDefender.
%R 10.18653/v1/2021.emnlp-main.251
%U https://aclanthology.org/2021.emnlp-main.251
%U https://doi.org/10.18653/v1/2021.emnlp-main.251
%P 3137-3147
Markdown (Informal)
[Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution](https://aclanthology.org/2021.emnlp-main.251) (Li et al., EMNLP 2021)
ACL
- Zongyi Li, Jianhan Xu, Jiehang Zeng, Linyang Li, Xiaoqing Zheng, Qi Zhang, Kai-Wei Chang, and Cho-Jui Hsieh. 2021. Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3137–3147, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.