[Caice-csse] AI+ Security: research from Norway on how to use LLMs for cryptographic communication

[N Narayanan]

An LLM Framework For Cryptography Over Chat Channels
We propose a novel cryptographic embedding framework that enables covert Public Key or Symmetric Key encrypted communication over public chat channels with humanlike 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.

https://arxiv.org/abs/2504.08871<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Farxiv.org%2Fabs%2F2504.08871&data=05%7C02%7Ccaice-csse%40eng.auburn.edu%7Cd55afd035569443ad7d408dd94787ea5%7Cccb6deedbd294b388979d72780f62d3b%7C0%7C0%7C638829967431961948%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=Qm8zDkosbmzULMT18kag47SjggT%2BhBpUBhi6pi1fT84%3D&reserved=0>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.eng.auburn.edu/pipermail/caice-csse/attachments/20250516/85eec7cb/attachment.htm>