<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2025-lost">
    <titleInfo>
        <title>Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiyang</namePart>
        <namePart type="family">Luo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ke</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chao</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahui</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lijie</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luo</namePart>
        <namePart type="family">Ping</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>The proliferation of large language models (LLMs) in generating content raises concerns about text copyright. Watermarking methods, particularly logit-based approaches, embed imperceptible identifiers into text to address these challenges. However, the widespread usage of watermarking across diverse LLMs has led to an inevitable issue known as watermark collision during common tasks, such as paraphrasing or translation.In this paper, we introduce watermark collision as a novel and general philosophy for watermark attacks, aimed at enhancing attack performance on top of any other attacking methods. We also provide a comprehensive demonstration that watermark collision poses a threat to all logit-based watermark algorithms, impacting not only specific attack scenarios but also downstream applications.</abstract>
    <identifier type="citekey">luo-etal-2025-lost</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-naacl.37</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-naacl.37/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>620</start>
            <end>637</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs
%A Luo, Yiyang
%A Lin, Ke
%A Gu, Chao
%A Hou, Jiahui
%A Wen, Lijie
%A Ping, Luo
%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 luo-etal-2025-lost
%X The proliferation of large language models (LLMs) in generating content raises concerns about text copyright. Watermarking methods, particularly logit-based approaches, embed imperceptible identifiers into text to address these challenges. However, the widespread usage of watermarking across diverse LLMs has led to an inevitable issue known as watermark collision during common tasks, such as paraphrasing or translation.In this paper, we introduce watermark collision as a novel and general philosophy for watermark attacks, aimed at enhancing attack performance on top of any other attacking methods. We also provide a comprehensive demonstration that watermark collision poses a threat to all logit-based watermark algorithms, impacting not only specific attack scenarios but also downstream applications.
%R 10.18653/v1/2025.findings-naacl.37
%U https://aclanthology.org/2025.findings-naacl.37/
%U https://doi.org/10.18653/v1/2025.findings-naacl.37
%P 620-637

Markdown (Informal)

[Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs](https://aclanthology.org/2025.findings-naacl.37/) (Luo et al., Findings 2025)

• Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs (Luo et al., Findings 2025)

ACL

• Yiyang Luo, Ke Lin, Chao Gu, Jiahui Hou, Lijie Wen, and Luo Ping. 2025. Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 620–637, Albuquerque, New Mexico. Association for Computational Linguistics.