<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2025-claim">
    <titleInfo>
        <title>Claim-Guided Textual Backdoor Attack for Practical Applications</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Minkyoo</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hanna</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaehan</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Youngjin</namePart>
        <namePart type="family">Jin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seungwon</namePart>
        <namePart type="family">Shin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-195-7</identifier>
    </relatedItem>
    <abstract>Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor attacks require input manipulation after model distribution to activate the backdoor, posing limitations in real-world applicability. Addressing this gap, we introduce a novel Claim-Guided Backdoor Attack (CGBA), which eliminates the need for such manipulations by utilizing inherent textual claims as triggers. CGBA leverages claim extraction, clustering, and targeted training to trick models to misbehave on targeted claims without affecting their performance on clean data. CGBA demonstrates its effectiveness and stealthiness across various datasets and models, significantly enhancing the feasibility of practical backdoor attacks. Our code and data will be available at https://github.com/minkyoo9/CGBA.</abstract>
    <identifier type="citekey">song-etal-2025-claim</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.64</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.64/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>1145</start>
            <end>1159</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Claim-Guided Textual Backdoor Attack for Practical Applications
%A Song, Minkyoo
%A Kim, Hanna
%A Kim, Jaehan
%A Jin, Youngjin
%A Shin, Seungwon
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F song-etal-2025-claim
%X Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor attacks require input manipulation after model distribution to activate the backdoor, posing limitations in real-world applicability. Addressing this gap, we introduce a novel Claim-Guided Backdoor Attack (CGBA), which eliminates the need for such manipulations by utilizing inherent textual claims as triggers. CGBA leverages claim extraction, clustering, and targeted training to trick models to misbehave on targeted claims without affecting their performance on clean data. CGBA demonstrates its effectiveness and stealthiness across various datasets and models, significantly enhancing the feasibility of practical backdoor attacks. Our code and data will be available at https://github.com/minkyoo9/CGBA.
%R 10.18653/v1/2025.findings-naacl.64
%U https://aclanthology.org/2025.findings-naacl.64/
%U https://doi.org/10.18653/v1/2025.findings-naacl.64
%P 1145-1159

Markdown (Informal)

[Claim-Guided Textual Backdoor Attack for Practical Applications](https://aclanthology.org/2025.findings-naacl.64/) (Song et al., Findings 2025)

• Claim-Guided Textual Backdoor Attack for Practical Applications (Song et al., Findings 2025)

ACL

• Minkyoo Song, Hanna Kim, Jaehan Kim, Youngjin Jin, and Seungwon Shin. 2025. Claim-Guided Textual Backdoor Attack for Practical Applications. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 1145–1159, Albuquerque, New Mexico. Association for Computational Linguistics.