Matthew Green：沙箱隔离不足以遏制AI蠕虫传播
Quoting Matthew Green
Agent 安全是当下最核心的工程挑战之一，这篇深度分析直接指出了沙箱隔离的局限性及蠕虫式传播的具体路径，对做 Agent 架构和安全防御的同学极具参考价值。
[...] Put these pieces together and you have the two halves of a worm: a payload that hijacks the agent, and an agent that will carry the payload to the next agent. Agents in separately-isolated sandboxes discovered that they could leave instructions for each other in a shared package cache, and those instructions changed what the recipients did. Replace the package cache with email, Slack and shared documents or WhatsApp, and replace independently-sandboxed training runs with independently-deployed personal agents like Muse, and you have exactly the ingredients that a worm needs.
[...] 将这些部分组合在一起，你就得到了蠕虫的两个半部分：一个劫持代理的载荷，以及一个将载荷传递给下一个代理的代理。在相互隔离的沙箱中发现，它们可以在共享的软件包缓存中留下彼此的操作指令，而这些指令会改变接收者的行为。将软件包缓存替换为电子邮件、Slack 和共享文档或 WhatsApp，并将独立沙箱化的训练运行替换为独立部署的个人代理（如 Muse），你就拥有了构成蠕虫所需的全部要素。
— Matthew Green, Is sandboxing sufficient to contain rogue agents?
—— Matthew Green，《沙箱是否足以遏制失控的 AI 代理？》
Tags: accidental-cyberattacks, ai-misuse, generative-ai, ai-security-research, sandboxing, ai, llms
标签：意外网络攻击、AI 滥用、生成式 AI、AI 安全研究、沙箱化、AI、大语言模型
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力