<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soumik-etal-2026-innocence">
    <titleInfo>
        <title>No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mohd.</namePart>
        <namePart type="given">Farhan</namePart>
        <namePart type="given">Israk</namePart>
        <namePart type="family">Soumik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Syed</namePart>
        <namePart type="given">Mhamudul</namePart>
        <namePart type="family">Hasan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wanniarachchi</namePart>
        <namePart type="given">Kankanamge</namePart>
        <namePart type="given">Malithi</namePart>
        <namePart type="family">Mithsara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ahmed</namePart>
        <namePart type="family">Imteaj</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abdur</namePart>
        <namePart type="given">R</namePart>
        <namePart type="family">Shahid</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>Generative AI writing assistants are now integrated into consumer platforms such as Apple Intelligence and Microsoft Copilot, enabling millions of users to automatically rewrite and stylize their text. While positioned as productivity tools, their deployment at scale introduces important and underexplored implications for privacy and platform safety. This paper examines the dual-use nature of platform-level text stylization. Stylization can enhance privacy by suppressing stylistic signals used for profiling and personal data inference. However, the same transformations can be leveraged to evade automated safeguards, including misinformation detection systems. We conduct empirical case studies on emotion inference and misinformation detection across benchmark datasets using deployed stylization modes. We evaluate downstream impact with fine-tuned open-source models and GPT-4o in a zero-shot setting. Our results show that stylization reduces emotion inference accuracy, lowering profiling risk, while increasing error rates in misinformation detection. This discovery reveal a measurable trade-off among privacy protection, moderation robustness, and stylization, highlighting new design and governance challenges for industry deployment.</abstract>
    <identifier type="citekey">soumik-etal-2026-innocence</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.128/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1866</start>
            <end>1885</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants
%A Soumik, Mohd. Farhan Israk
%A Hasan, Syed Mhamudul
%A Mithsara, Wanniarachchi Kankanamge Malithi
%A Imteaj, Ahmed
%A Shahid, Abdur R.
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F soumik-etal-2026-innocence
%X Generative AI writing assistants are now integrated into consumer platforms such as Apple Intelligence and Microsoft Copilot, enabling millions of users to automatically rewrite and stylize their text. While positioned as productivity tools, their deployment at scale introduces important and underexplored implications for privacy and platform safety. This paper examines the dual-use nature of platform-level text stylization. Stylization can enhance privacy by suppressing stylistic signals used for profiling and personal data inference. However, the same transformations can be leveraged to evade automated safeguards, including misinformation detection systems. We conduct empirical case studies on emotion inference and misinformation detection across benchmark datasets using deployed stylization modes. We evaluate downstream impact with fine-tuned open-source models and GPT-4o in a zero-shot setting. Our results show that stylization reduces emotion inference accuracy, lowering profiling risk, while increasing error rates in misinformation detection. This discovery reveal a measurable trade-off among privacy protection, moderation robustness, and stylization, highlighting new design and governance challenges for industry deployment.
%U https://aclanthology.org/2026.acl-industry.128/
%P 1866-1885

Markdown (Informal)

[No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants](https://aclanthology.org/2026.acl-industry.128/) (Soumik et al., ACL 2026)

• No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants (Soumik et al., ACL 2026)

ACL

• Mohd. Farhan Israk Soumik, Syed Mhamudul Hasan, Wanniarachchi Kankanamge Malithi Mithsara, Ahmed Imteaj, and Abdur R. Shahid. 2026. No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1866–1885, San Diego, California, USA. Association for Computational Linguistics.