PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words

Yuzhi Liang; Shiliang Xiao; Jingsong Wei; Qiliang Lin; Xia Li

PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words

Yuzhi Liang, Shiliang Xiao, Jingsong Wei, Qiliang Lin, Xia Li

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Existing hard-label text attacks often rely on inefficient "outside-in" strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient "inside-out" framework. It employs a Multi-Armed Bandit algorithm to identify Pivot Sets—combinatorial token groups acting as prediction anchors—and strategically perturbs them to induce label flips. This approach captures inter-word dependencies and minimizes query costs. Extensive experiments across traditional models and Large Language Models demonstrate that PivotAttack consistently outperforms state-of-the-art baselines in both Attack Success Rate and query efficiency.

Anthology ID:: 2026.findings-acl.157
Volume:: Findings of the Association for Computational Linguistics: ACL 2026
Month:: July
Year:: 2026
Address:: San Diego, California, United States
Editors:: Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 3190–3207
Language:
URL:: https://aclanthology.org/2026.findings-acl.157/
DOI:
Bibkey:
Cite (ACL):: Yuzhi Liang, Shiliang Xiao, Jingsong Wei, Qiliang Lin, and Xia Li. 2026. PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words. In Findings of the Association for Computational Linguistics: ACL 2026, pages 3190–3207, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):: PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words (Liang et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-acl.157.pdf
Checklist:: 2026.findings-acl.157.checklist.pdf

PDF Cite Search Checklist Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{liang-etal-2026-pivotattack,
    title = "{P}ivot{A}ttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words",
    author = "Liang, Yuzhi  and
      Xiao, Shiliang  and
      Wei, Jingsong  and
      Lin, Qiliang  and
      Li, Xia",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-acl.157/",
    pages = "3190--3207",
    ISBN = "979-8-89176-395-1",
    abstract = "Existing hard-label text attacks often rely on inefficient ``outside-in'' strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient ``inside-out'' framework. It employs a Multi-Armed Bandit algorithm to identify Pivot Sets{---}combinatorial token groups acting as prediction anchors{---}and strategically perturbs them to induce label flips. This approach captures inter-word dependencies and minimizes query costs. Extensive experiments across traditional models and Large Language Models demonstrate that PivotAttack consistently outperforms state-of-the-art baselines in both Attack Success Rate and query efficiency."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2026-pivotattack">
    <titleInfo>
        <title>PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuzhi</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shiliang</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingsong</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qiliang</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xia</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Existing hard-label text attacks often rely on inefficient “outside-in” strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient “inside-out” framework. It employs a Multi-Armed Bandit algorithm to identify Pivot Sets—combinatorial token groups acting as prediction anchors—and strategically perturbs them to induce label flips. This approach captures inter-word dependencies and minimizes query costs. Extensive experiments across traditional models and Large Language Models demonstrate that PivotAttack consistently outperforms state-of-the-art baselines in both Attack Success Rate and query efficiency.</abstract>
    <identifier type="citekey">liang-etal-2026-pivotattack</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.157/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>3190</start>
            <end>3207</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words
%A Liang, Yuzhi
%A Xiao, Shiliang
%A Wei, Jingsong
%A Lin, Qiliang
%A Li, Xia
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liang-etal-2026-pivotattack
%X Existing hard-label text attacks often rely on inefficient “outside-in” strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient “inside-out” framework. It employs a Multi-Armed Bandit algorithm to identify Pivot Sets—combinatorial token groups acting as prediction anchors—and strategically perturbs them to induce label flips. This approach captures inter-word dependencies and minimizes query costs. Extensive experiments across traditional models and Large Language Models demonstrate that PivotAttack consistently outperforms state-of-the-art baselines in both Attack Success Rate and query efficiency.
%U https://aclanthology.org/2026.findings-acl.157/
%P 3190-3207

Download as File

Markdown (Informal)

[PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words](https://aclanthology.org/2026.findings-acl.157/) (Liang et al., Findings 2026)

PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words (Liang et al., Findings 2026)

ACL

Yuzhi Liang, Shiliang Xiao, Jingsong Wei, Qiliang Lin, and Xia Li. 2026. PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words. In Findings of the Association for Computational Linguistics: ACL 2026, pages 3190–3207, San Diego, California, United States. Association for Computational Linguistics.