[2510.20075] LLMs can hide text in other text of the same length

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Artificial Intelligence

arXiv:2510.20075 (cs)

[Submitted on 22 Oct 2025 (v1), last revised 16 Jan 2026 (this version, v6)]

Title:LLMs can hide text in other text of the same length

Authors:Antonio Norelli, Michael Bronstein<br>View a PDF of the paper titled LLMs can hide text in other text of the same length, by Antonio Norelli and Michael Bronstein

View PDF

Abstract:A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conceal a secret manuscript. This uncanny state of affairs is now possible thanks to Large Language Models, and in this paper we present Calgacus, a simple and efficient protocol to achieve it. We show that even modest 8-billion-parameter open-source LLMs are sufficient to obtain high-quality results, and a message as long as this abstract can be encoded and decoded locally on a laptop in seconds. The existence of such a protocol demonstrates a radical decoupling of text from authorial intent, further eroding trust in written communication, already shaken by the rise of LLM chatbots. We illustrate this with a concrete scenario: a company could covertly deploy an unfiltered LLM by encoding its answers within the compliant responses of a safe model. This possibility raises urgent questions for AI safety and challenges our understanding of what it means for a Large Language Model to know something.

Comments:<br>21 pages, main paper 9 pages. v5 contains an Italian translation of this paper by the author

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR); Machine Learning (cs.LG)

Cite as:<br>arXiv:2510.20075 [cs.AI]

(or<br>arXiv:2510.20075v6 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2510.20075

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Antonio Norelli [view email]<br>[v1]<br>Wed, 22 Oct 2025 23:16:50 UTC (4,955 KB)

[v2]<br>Fri, 24 Oct 2025 14:59:45 UTC (4,955 KB)

[v3]<br>Mon, 27 Oct 2025 13:54:40 UTC (4,955 KB)

[v4]<br>Mon, 1 Dec 2025 17:01:54 UTC (4,956 KB)

[v5]<br>Mon, 5 Jan 2026 11:25:29 UTC (10,112 KB)

[v6]<br>Fri, 16 Jan 2026 14:08:21 UTC (4,984 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled LLMs can hide text in other text of the same length, by Antonio Norelli and Michael Bronstein<br>View PDF<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2025-10

Change to browse by:

cs<br>cs.CL<br>cs.CR<br>cs.LG

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from