Linguistic Steganography via Self-Adjusting Asymmetric Number System

Yiting Liu; Chungen Xu; Fei Yang; Pan Zhang; Linlong Wang

doi:10.1162/coli.a.22

Linguistic Steganography via Self-Adjusting Asymmetric Number System

Yiting Liu, Chungen Xu, Fei Yang, Pan Zhang, Linlong Wang

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

Linguistic steganography (stego) seeks to conceal secret information within natural language text. However, existing methods often struggle to balance stego text quality with embedding efficiency, largely due to limitations in generation strategies and coding mechanisms. We propose SA-ANS, a self-adaptive linguistic steganography framework based on a self-adjusting Asymmetric Numeral System. SA-ANS allows user-specified embedding rates and uses probabilistic coding with adaptive candidate selection, dynamically tailoring the token pool to the language model’s probability distribution. This design produces fluent, semantically coherent stego text while preserving statistical indistinguishability from natural language. Extensive experiments on multiple benchmark datasets, evaluated across embedding efficiency, linguistic quality, statistical similarity, robustness to steganalysis, and human judgment, show that SA-ANS consistently outperforms state-of-the-art methods, demonstrating both effectiveness and practicality.

Anthology ID:: 2026.cl-1.4
Volume:: Computational Linguistics, Volume 52, Issue 1 - March 2026
Month:: March
Year:: 2026
Address:: Cambridge, MA
Venue:: CL
SIG:
Publisher:: MIT Press
Note:
Pages:: 113–149
Language:
URL:: https://aclanthology.org/2026.cl-1.4/
DOI:: 10.1162/coli.a.22
Bibkey:
Cite (ACL):: Yiting Liu, Chungen Xu, Fei Yang, Pan Zhang, and Linlong Wang. 2026. Linguistic Steganography via Self-Adjusting Asymmetric Number System. Computational Linguistics, 52(1):113–149.
Cite (Informal):: Linguistic Steganography via Self-Adjusting Asymmetric Number System (Liu et al., CL 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.cl-1.4.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@article{liu-etal-2026-linguistic,
    title = "Linguistic Steganography via Self-Adjusting Asymmetric Number System",
    author = "Liu, Yiting  and
      Xu, Chungen  and
      Yang, Fei  and
      Zhang, Pan  and
      Wang, Linlong",
    journal = "Computational Linguistics",
    volume = "52",
    number = "1",
    month = mar,
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2026.cl-1.4/",
    doi = "10.1162/coli.a.22",
    pages = "113--149",
    abstract = "Linguistic steganography (stego) seeks to conceal secret information within natural language text. However, existing methods often struggle to balance stego text quality with embedding efficiency, largely due to limitations in generation strategies and coding mechanisms. We propose SA-ANS, a self-adaptive linguistic steganography framework based on a self-adjusting Asymmetric Numeral System. SA-ANS allows user-specified embedding rates and uses probabilistic coding with adaptive candidate selection, dynamically tailoring the token pool to the language model{'}s probability distribution. This design produces fluent, semantically coherent stego text while preserving statistical indistinguishability from natural language. Extensive experiments on multiple benchmark datasets, evaluated across embedding efficiency, linguistic quality, statistical similarity, robustness to steganalysis, and human judgment, show that SA-ANS consistently outperforms state-of-the-art methods, demonstrating both effectiveness and practicality."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-linguistic">
    <titleInfo>
        <title>Linguistic Steganography via Self-Adjusting Asymmetric Number System</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiting</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chungen</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fei</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Linlong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Linguistic steganography (stego) seeks to conceal secret information within natural language text. However, existing methods often struggle to balance stego text quality with embedding efficiency, largely due to limitations in generation strategies and coding mechanisms. We propose SA-ANS, a self-adaptive linguistic steganography framework based on a self-adjusting Asymmetric Numeral System. SA-ANS allows user-specified embedding rates and uses probabilistic coding with adaptive candidate selection, dynamically tailoring the token pool to the language model’s probability distribution. This design produces fluent, semantically coherent stego text while preserving statistical indistinguishability from natural language. Extensive experiments on multiple benchmark datasets, evaluated across embedding efficiency, linguistic quality, statistical similarity, robustness to steganalysis, and human judgment, show that SA-ANS consistently outperforms state-of-the-art methods, demonstrating both effectiveness and practicality.</abstract>
    <identifier type="citekey">liu-etal-2026-linguistic</identifier>
    <identifier type="doi">10.1162/coli.a.22</identifier>
    <location>
        <url>https://aclanthology.org/2026.cl-1.4/</url>
    </location>
    <part>
        <date>2026-03</date>
        <detail type="volume"><number>52</number></detail>
        <detail type="issue"><number>1</number></detail>
        <extent unit="page">
            <start>113</start>
            <end>149</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Journal Article
%T Linguistic Steganography via Self-Adjusting Asymmetric Number System
%A Liu, Yiting
%A Xu, Chungen
%A Yang, Fei
%A Zhang, Pan
%A Wang, Linlong
%J Computational Linguistics
%D 2026
%8 March
%V 52
%N 1
%I MIT Press
%C Cambridge, MA
%F liu-etal-2026-linguistic
%X Linguistic steganography (stego) seeks to conceal secret information within natural language text. However, existing methods often struggle to balance stego text quality with embedding efficiency, largely due to limitations in generation strategies and coding mechanisms. We propose SA-ANS, a self-adaptive linguistic steganography framework based on a self-adjusting Asymmetric Numeral System. SA-ANS allows user-specified embedding rates and uses probabilistic coding with adaptive candidate selection, dynamically tailoring the token pool to the language model’s probability distribution. This design produces fluent, semantically coherent stego text while preserving statistical indistinguishability from natural language. Extensive experiments on multiple benchmark datasets, evaluated across embedding efficiency, linguistic quality, statistical similarity, robustness to steganalysis, and human judgment, show that SA-ANS consistently outperforms state-of-the-art methods, demonstrating both effectiveness and practicality.
%R 10.1162/coli.a.22
%U https://aclanthology.org/2026.cl-1.4/
%U https://doi.org/10.1162/coli.a.22
%P 113-149

Download as File

Markdown (Informal)

[Linguistic Steganography via Self-Adjusting Asymmetric Number System](https://aclanthology.org/2026.cl-1.4/) (Liu et al., CL 2026)

Linguistic Steganography via Self-Adjusting Asymmetric Number System (Liu et al., CL 2026)

ACL

Yiting Liu, Chungen Xu, Fei Yang, Pan Zhang, and Linlong Wang. 2026. Linguistic Steganography via Self-Adjusting Asymmetric Number System. Computational Linguistics, 52(1):113–149.