Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916862497914880 |
|---|---|
| author | Motwani, Sumeet Ramesh Baranchuk, Mikhail Strohmeier, Martin Bolina, Vijay Torr, Philip H. S. Hammond, Lewis de Witt, Christian Schroeder |
| author_facet | Motwani, Sumeet Ramesh Baranchuk, Mikhail Strohmeier, Martin Bolina, Vijay Torr, Philip H. S. Hammond, Lewis de Witt, Christian Schroeder |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07510 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Secret Collusion among AI Agents: Multi-Agent Deception via Steganography Motwani, Sumeet Ramesh Baranchuk, Mikhail Strohmeier, Martin Bolina, Vijay Torr, Philip H. S. Hammond, Lewis de Witt, Christian Schroeder Artificial Intelligence Cryptography and Security 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. |
| title | Secret Collusion among AI Agents: Multi-Agent Deception via Steganography |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2402.07510 |