@inproceedings{tomonari-etal-2022-robustness,
title = "Robustness Evaluation of Text Classification Models Using Mathematical Optimization and Its Application to Adversarial Training",
author = "Tomonari, Hikaru and
Nishino, Masaaki and
Yamamoto, Akihiro",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.31",
pages = "327--333",
abstract = "Neural networks are known to be vulnerable to adversarial examples due to slightly perturbed input data. In practical applications of neural network models, the robustness of the models against perturbations must be evaluated. However, no method can strictly evaluate their robustness in natural language domains. We therefore propose a method that evaluates the robustness of text classification models using an integer linear programming (ILP) solver by an optimization problem that identifies a minimum synonym swap that changes the classification result. Our method allows us to compare the robustness of various models in realistic time. It can also be used for obtaining adversarial examples. Because of the minimal impact on the altered sentences, adversarial examples with our method obtained high scores in human evaluations of grammatical correctness and semantic similarity for an IMDb dataset. In addition, we implemented adversarial training with the IMDb and SST2 datasets and found that our adversarial training method makes the model robust.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tomonari-etal-2022-robustness">
<titleInfo>
<title>Robustness Evaluation of Text Classification Models Using Mathematical Optimization and Its Application to Adversarial Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hikaru</namePart>
<namePart type="family">Tomonari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nishino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akihiro</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural networks are known to be vulnerable to adversarial examples due to slightly perturbed input data. In practical applications of neural network models, the robustness of the models against perturbations must be evaluated. However, no method can strictly evaluate their robustness in natural language domains. We therefore propose a method that evaluates the robustness of text classification models using an integer linear programming (ILP) solver by an optimization problem that identifies a minimum synonym swap that changes the classification result. Our method allows us to compare the robustness of various models in realistic time. It can also be used for obtaining adversarial examples. Because of the minimal impact on the altered sentences, adversarial examples with our method obtained high scores in human evaluations of grammatical correctness and semantic similarity for an IMDb dataset. In addition, we implemented adversarial training with the IMDb and SST2 datasets and found that our adversarial training method makes the model robust.</abstract>
<identifier type="citekey">tomonari-etal-2022-robustness</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.31</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>327</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robustness Evaluation of Text Classification Models Using Mathematical Optimization and Its Application to Adversarial Training
%A Tomonari, Hikaru
%A Nishino, Masaaki
%A Yamamoto, Akihiro
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F tomonari-etal-2022-robustness
%X Neural networks are known to be vulnerable to adversarial examples due to slightly perturbed input data. In practical applications of neural network models, the robustness of the models against perturbations must be evaluated. However, no method can strictly evaluate their robustness in natural language domains. We therefore propose a method that evaluates the robustness of text classification models using an integer linear programming (ILP) solver by an optimization problem that identifies a minimum synonym swap that changes the classification result. Our method allows us to compare the robustness of various models in realistic time. It can also be used for obtaining adversarial examples. Because of the minimal impact on the altered sentences, adversarial examples with our method obtained high scores in human evaluations of grammatical correctness and semantic similarity for an IMDb dataset. In addition, we implemented adversarial training with the IMDb and SST2 datasets and found that our adversarial training method makes the model robust.
%U https://aclanthology.org/2022.findings-aacl.31
%P 327-333
Markdown (Informal)
[Robustness Evaluation of Text Classification Models Using Mathematical Optimization and Its Application to Adversarial Training](https://aclanthology.org/2022.findings-aacl.31) (Tomonari et al., Findings 2022)
ACL