按年被提到
20242024 · 1 次2026
AI 安全、伦理与社会影响›提示注入与对齐风险·arXiv:2402.07510 · cs.AI

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography

Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H. S. Torr, Lewis Hammond, Christian Schroeder de Witt · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-02-13 · 最近 2026-09-07
2不同的人
2活跃月份
2讨论串
31被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)

讨论串里没有 ≥100 字的评论,只有提交记录。

被提交为 story · 2 次