{"slug": "undetectable-conversations-between-ai-agents-via-noise-resilient-key-exchange", "title": "Undetectable Conversations Between AI Agents via Noise-Resilient Key Exchange", "summary": "A paper submitted to arXiv on 6 April 2026 shows that two AI agents operated by different entities can conduct an undetectable parallel secret conversation whose transcript is computationally indistinguishable from an honest interaction, even to a strong passive auditor holding the full model descriptions, protocol, and the agents' private contexts. The authors introduce a new cryptographic primitive they call pseudorandom noise-resilient key exchange, which enables covert key exchange in the keyless setting where agents share no initial secret, assuming only that sufficiently many individual messages have at least constant min-entropy. The paper concludes that transcript auditing alone cannot rule out covert coordination between AI agents.", "body_md": "# Computer Science > Cryptography and Security\n\n  [Submitted on 6 Apr 2026]\n\n# Title:Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange\n\n[View PDF](https://arxiv.org/pdf/2604.04757)\n\n[HTML (experimental)](https://arxiv.org/html/2604.04757v1)\n\nAbstract:AI agents are increasingly deployed to interact with other agents on behalf of users and organizations. We ask whether two such agents, operated by different entities, can carry out a parallel secret conversation while still producing a transcript that is computationally indistinguishable from an honest interaction, even to a strong passive auditor that knows the full model descriptions, the protocol, and the agents' private contexts. Building on recent work on watermarking and steganography for LLMs, we first show that if the parties possess an interaction-unique secret key, they can facilitate an optimal-rate covert conversation: the hidden conversation can exploit essentially all of the entropy present in the honest message distributions.\n\nOur main contributions concern extending this to the keyless setting, where the agents begin with no shared secret. We show that covert key exchange, and hence covert conversation, is possible even when each model has an arbitrary private context, and their messages are short and fully adaptive, assuming only that sufficiently many individual messages have at least constant min-entropy. This stands in contrast to previous covert communication works, which relied on the min-entropy in each individual message growing with the security parameter. To obtain this, we introduce a new cryptographic primitive, which we call pseudorandom noise-resilient key exchange: a key-exchange protocol whose public transcript is pseudorandom while still remaining correct under constant noise. We study this primitive, giving several constructions relevant to our application as well as strong limitations showing that more naive variants are impossible or vulnerable to efficient attacks.\n\nThese results show that transcript auditing alone cannot rule out covert coordination between AI agents, and identify a new cryptographic theory that may be of independent interest.\n\n### Current browse context:\n\ncs.CR\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/undetectable-conversations-between-ai-agents-via-noise-resilient-key-exchange", "canonical_source": "https://arxiv.org/abs/2604.04757", "published_at": "2026-09-22 14:19:38+00:00", "updated_at": "2026-09-22 14:24:39.973079+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "ai-research", "artificial-intelligence"], "entities": ["arXiv", "pseudorandom noise-resilient key exchange"], "alternates": {"html": "https://wpnews.pro/news/undetectable-conversations-between-ai-agents-via-noise-resilient-key-exchange", "markdown": "https://wpnews.pro/news/undetectable-conversations-between-ai-agents-via-noise-resilient-key-exchange.md", "text": "https://wpnews.pro/news/undetectable-conversations-between-ai-agents-via-noise-resilient-key-exchange.txt", "jsonld": "https://wpnews.pro/news/undetectable-conversations-between-ai-agents-via-noise-resilient-key-exchange.jsonld"}}