Paper 2025/661

An LLM Framework For Cryptography Over Chat Channels

Danilo Gligoroski, Norwegian University of Science and Technology
Mayank Raikwar, University of Oslo
Sonu Kumar Jha, Norwegian University of Science and Technology
Abstract

Recent advancements in Large Language Models (LLMs) have transformed communication, yet their role in secure messaging remains underexplored, especially in surveillance-heavy environments. At the same time, many governments all over the world are proposing legislation to detect, backdoor, or even ban encrypted communication. That emphasizes the need for alternative ways to communicate securely and covertly over open channels. We propose a novel cryptographic embedding framework that enables covert Public Key or Symmetric Key encrypted communication over public chat channels with human-like produced texts. Some unique properties of our framework are: 1. It is LLM agnostic, i.e., it allows participants to use different local LLM models independently; 2. It is pre- or post-quantum agnostic; 3. It ensures indistinguishability from human-like chat-produced texts. Thus, it offers a viable alternative where traditional encryption is detectable and restricted.

Metadata
Available format(s)
PDF
Category
Cryptographic protocols
Publication info
Preprint.
Keywords
LLMsTransformersSteganographyWatermarkingCryptography
Contact author(s)
danilog @ ntnu no
mayankr @ ifi uio no
sonu k jha @ ntnu no
History
2025-04-13: approved
2025-04-11: received
See all versions
Short URL
https://ia.cr/2025/661
License
Creative Commons Attribution-NonCommercial-NoDerivs
CC BY-NC-ND

BibTeX

@misc{cryptoeprint:2025/661,
      author = {Danilo Gligoroski and Mayank Raikwar and Sonu Kumar Jha},
      title = {An {LLM} Framework For Cryptography Over Chat Channels},
      howpublished = {Cryptology {ePrint} Archive, Paper 2025/661},
      year = {2025},
      url = {https://eprint.iacr.org/2025/661}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.