<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2021-transferability">
    <titleInfo>
        <title>On the Transferability of Adversarial Attacks against Neural Text Classifier</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liping</namePart>
        <namePart type="family">Yuan</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">Yi</namePart>
        <namePart type="family">Zhou</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>
    <name type="personal">
        <namePart type="given">Kai-Wei</namePart>
        <namePart type="family">Chang</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>
        <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>Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we present the first study to systematically investigate the transferability of adversarial examples for text classification models and explore how various factors, including network architecture, tokenization scheme, word embedding, and model capacity, affect the transferability of adversarial examples. Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models. Such adversarial examples reflect the defects of the learning process and the data bias in the training set. Finally, we derive word replacement rules that can be used for model diagnostics from these adversarial examples.</abstract>
    <identifier type="citekey">yuan-etal-2021-transferability</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.121</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.121</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>1612</start>
            <end>1625</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the Transferability of Adversarial Attacks against Neural Text Classifier
%A Yuan, Liping
%A Zheng, Xiaoqing
%A Zhou, Yi
%A Hsieh, Cho-Jui
%A Chang, Kai-Wei
%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 yuan-etal-2021-transferability
%X Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we present the first study to systematically investigate the transferability of adversarial examples for text classification models and explore how various factors, including network architecture, tokenization scheme, word embedding, and model capacity, affect the transferability of adversarial examples. Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models. Such adversarial examples reflect the defects of the learning process and the data bias in the training set. Finally, we derive word replacement rules that can be used for model diagnostics from these adversarial examples.
%R 10.18653/v1/2021.emnlp-main.121
%U https://aclanthology.org/2021.emnlp-main.121
%U https://doi.org/10.18653/v1/2021.emnlp-main.121
%P 1612-1625

Markdown (Informal)

[On the Transferability of Adversarial Attacks against Neural Text Classifier](https://aclanthology.org/2021.emnlp-main.121) (Yuan et al., EMNLP 2021)

• On the Transferability of Adversarial Attacks against Neural Text Classifier (Yuan et al., EMNLP 2021)

ACL

• Liping Yuan, Xiaoqing Zheng, Yi Zhou, Cho-Jui Hsieh, and Kai-Wei Chang. 2021. On the Transferability of Adversarial Attacks against Neural Text Classifier. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1612–1625, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.