<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2024-query">
    <titleInfo>
        <title>Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhen</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhenhua</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kun</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Deep neural networks for Natural Language Processing (NLP) have been demonstrated to be vulnerable to textual adversarial examples. Existing black-box attacks typically require thousands of queries on the target model, making them expensive in real-world applications. In this paper, we propose a new approach that guides the word substitutions using prior knowledge from the training set to improve the attack efficiency. Specifically, we introduce Adversarial Boosting Preference (ABP), a metric that quantifies the importance of words and guides adversarial word substitutions. We then propose two query-efficient attack strategies based on ABP: query-free attack (ABP_free) and guided search attack (ABP_guide). Extensive evaluations for text classification demonstrate that ABP_free generates more natural adversarial examples than existing universal attacks, ABP_guide significantly reduces the number of queries by a factor of 10 500 while achieving comparable or even better performance than black-box attack baselines. Furthermore, we introduce the first ensemble attack ABP_ens in NLP, which gains further performance improvements and achieves better transferability and generalization by the ensemble of the ABP across different models and domains. Code is available at https://github.com/BaiDingHub/ABP.</abstract>
    <identifier type="citekey">yu-etal-2024-query</identifier>
    <location>
        <url>https://aclanthology.org/2024.naacl-long.31</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>556</start>
            <end>569</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks
%A Yu, Zhen
%A Chen, Zhenhua
%A He, Kun
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F yu-etal-2024-query
%X Deep neural networks for Natural Language Processing (NLP) have been demonstrated to be vulnerable to textual adversarial examples. Existing black-box attacks typically require thousands of queries on the target model, making them expensive in real-world applications. In this paper, we propose a new approach that guides the word substitutions using prior knowledge from the training set to improve the attack efficiency. Specifically, we introduce Adversarial Boosting Preference (ABP), a metric that quantifies the importance of words and guides adversarial word substitutions. We then propose two query-efficient attack strategies based on ABP: query-free attack (ABP_free) and guided search attack (ABP_guide). Extensive evaluations for text classification demonstrate that ABP_free generates more natural adversarial examples than existing universal attacks, ABP_guide significantly reduces the number of queries by a factor of 10 500 while achieving comparable or even better performance than black-box attack baselines. Furthermore, we introduce the first ensemble attack ABP_ens in NLP, which gains further performance improvements and achieves better transferability and generalization by the ensemble of the ABP across different models and domains. Code is available at https://github.com/BaiDingHub/ABP.
%U https://aclanthology.org/2024.naacl-long.31
%P 556-569

Markdown (Informal)

[Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks](https://aclanthology.org/2024.naacl-long.31) (Yu et al., NAACL 2024)

• Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks (Yu et al., NAACL 2024)

ACL

• Zhen Yu, Zhenhua Chen, and Kun He. 2024. Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 556–569, Mexico City, Mexico. Association for Computational Linguistics.