@inproceedings{xu-etal-2021-grey,
title = "Grey-box Adversarial Attack And Defence For Sentiment Classification",
author = "Xu, Ying and
Zhong, Xu and
Jimeno Yepes, Antonio and
Lau, Jey Han",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.321",
doi = "10.18653/v1/2021.naacl-main.321",
pages = "4078--4087",
abstract = "We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-grey">
<titleInfo>
<title>Grey-box Adversarial Attack And Defence For Sentiment Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jey</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.</abstract>
<identifier type="citekey">xu-etal-2021-grey</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.321</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.321</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>4078</start>
<end>4087</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grey-box Adversarial Attack And Defence For Sentiment Classification
%A Xu, Ying
%A Zhong, Xu
%A Jimeno Yepes, Antonio
%A Lau, Jey Han
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F xu-etal-2021-grey
%X We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.
%R 10.18653/v1/2021.naacl-main.321
%U https://aclanthology.org/2021.naacl-main.321
%U https://doi.org/10.18653/v1/2021.naacl-main.321
%P 4078-4087
Markdown (Informal)
[Grey-box Adversarial Attack And Defence For Sentiment Classification](https://aclanthology.org/2021.naacl-main.321) (Xu et al., NAACL 2021)
ACL
- Ying Xu, Xu Zhong, Antonio Jimeno Yepes, and Jey Han Lau. 2021. Grey-box Adversarial Attack And Defence For Sentiment Classification. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4078–4087, Online. Association for Computational Linguistics.