Secret Collusion Among AI Agents

A paper submitted to arXiv on 12 Feb 2024 and revised through 25 Jul 2025 formalizes the problem of secret collusion among generative AI agents via steganography, finding that while current models' steganographic capabilities remain limited, GPT-4 shows a capability jump warranting continuous monitoring. The authors propose a model evaluation framework and mitigation measures to address privacy and security risks from unauthorized information sharing or unwanted coordination among AI agents.

Computer Science Artificial Intelligence Submitted on 12 Feb 2024 v1 https://arxiv.org/abs/2402.07510v1 , last revised 25 Jul 2025 this version, v5 Title:Secret Collusion among AI Agents: Multi-Agent Deception via Steganography View PDF /pdf/2402.07510 HTML experimental https://arxiv.org/html/2402.07510v5 Abstract:Recent capability increases in large language models LLMs open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and security challenges concerning the unauthorised sharing of information, or other unwanted forms of agent coordination. Modern steganographic techniques could render such dynamics hard to detect. In this paper, we comprehensively formalise the problem of secret collusion in systems of generative AI agents by drawing on relevant concepts from both AI and security literature. We study incentives for the use of steganography, and propose a variety of mitigation measures. Our investigations result in a model evaluation framework that systematically tests capabilities required for various forms of secret collusion. We provide extensive empirical results across a range of contemporary LLMs. While the steganographic capabilities of current models remain limited, GPT-4 displays a capability jump suggesting the need for continuous monitoring of steganographic frontier model capabilities. We conclude by laying out a comprehensive research program to mitigate future risks of collusion between generative AI models. Submission history From: Christian Schroeder de Witt view email /show-email/020dae4b/2402.07510 Mon, 12 Feb 2024 09:31:21 UTC 841 KB \ v1\ /abs/2402.07510v1 Wed, 28 Aug 2024 15:53:04 UTC 2,738 KB \ v2\ /abs/2402.07510v2 Fri, 8 Nov 2024 14:46:40 UTC 2,759 KB \ v3\ /abs/2402.07510v3 Mon, 14 Apr 2025 10:17:38 UTC 2,759 KB \ v4\ /abs/2402.07510v4 v5 Fri, 25 Jul 2025 12:28:15 UTC 564 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender 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 https://info.arxiv.org/labs/index.html .