Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?

Chengda Lu; Xiaoyu Fan; Yu Huang; Rongwu Xu; Jijie Li; Wei Xu

doi:10.18653/v1/2025.findings-acl.339

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?

Chengda Lu, Xiaoyu Fan, Yu Huang, Rongwu Xu, Jijie Li, Wei Xu

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

Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance validates our theoretical findings.

Anthology ID:: 2025.findings-acl.339
Volume:: Findings of the Association for Computational Linguistics: ACL 2025
Month:: July
Year:: 2025
Address:: Vienna, Austria
Editors:: Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:: Findings
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 6523–6546
Language:
URL:: https://aclanthology.org/2025.findings-acl.339/
DOI:: 10.18653/v1/2025.findings-acl.339
Bibkey:
Cite (ACL):: Chengda Lu, Xiaoyu Fan, Yu Huang, Rongwu Xu, Jijie Li, and Wei Xu. 2025. Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?. In Findings of the Association for Computational Linguistics: ACL 2025, pages 6523–6546, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):: Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking? (Lu et al., Findings 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.findings-acl.339.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{lu-etal-2025-chain,
    title = "Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?",
    author = "Lu, Chengda  and
      Fan, Xiaoyu  and
      Huang, Yu  and
      Xu, Rongwu  and
      Li, Jijie  and
      Xu, Wei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.339/",
    doi = "10.18653/v1/2025.findings-acl.339",
    pages = "6523--6546",
    ISBN = "979-8-89176-256-5",
    abstract = "Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance validates our theoretical findings."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2025-chain">
    <titleInfo>
        <title>Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chengda</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyu</namePart>
        <namePart type="family">Fan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rongwu</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jijie</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance validates our theoretical findings.</abstract>
    <identifier type="citekey">lu-etal-2025-chain</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.339</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.339/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>6523</start>
            <end>6546</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
%A Lu, Chengda
%A Fan, Xiaoyu
%A Huang, Yu
%A Xu, Rongwu
%A Li, Jijie
%A Xu, Wei
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F lu-etal-2025-chain
%X Jailbreak attacks have been observed to largely fail against recent reasoning models enhanced by Chain-of-Thought (CoT) reasoning. However, the underlying mechanism remains underexplored, and relying solely on reasoning capacity may raise security concerns. In this paper, we try to answer the question: Does CoT reasoning really reduce harmfulness from jailbreaking? Through rigorous theoretical analysis, we demonstrate that CoT reasoning has dual effects on jailbreaking harmfulness. Based on the theoretical insights, we propose a novel jailbreak method, FicDetail, whose practical performance validates our theoretical findings.
%R 10.18653/v1/2025.findings-acl.339
%U https://aclanthology.org/2025.findings-acl.339/
%U https://doi.org/10.18653/v1/2025.findings-acl.339
%P 6523-6546

Download as File

Markdown (Informal)

[Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?](https://aclanthology.org/2025.findings-acl.339/) (Lu et al., Findings 2025)

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking? (Lu et al., Findings 2025)

ACL

Chengda Lu, Xiaoyu Fan, Yu Huang, Rongwu Xu, Jijie Li, and Wei Xu. 2025. Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?. In Findings of the Association for Computational Linguistics: ACL 2025, pages 6523–6546, Vienna, Austria. Association for Computational Linguistics.