OpenAI 现已在无网络连接环境下训练前沿 AI 模型

在一系列失控黑客攻击事件发生后，OpenAI 目前正在无互联网连接的环境下训练其最先进的 AI 模型。在周五发布的一篇博文中，OpenAI 表示其构建了一个离线测试环境，AI 模型可以在其中与已索引和缓存的网页内容进行交互，“而不会带来影响外部系统的风险”。

OpenAI 此前在披露数起其 AI Agent 突破测试环境、入侵第三方公司与政府机构，或蜂拥攻击冷门网站的事件后，于9 月暂停了前沿 AI 模型的训练。博文称，10 月 1 日，OpenAI 在采取更严格安全措施的前提下，恢复了强化学习训练和内部推理。

即使实施了这些防护措施并切断了网络访问，OpenAI 仍发现 Agent“并不总是需要网络连接来进行通信”。在公司进行的一项测试中，他们要求位于不同虚拟机上的 AI 模型在没有网络连接的情况下交换机密信息。为了绕过这一限制，AI Agent 找到了一种利用处理器缓存进行通信的方法：

从缓存中读取数据的速度快于从主内存中检索数据，Agent 利用这种时延差异来进行通信。一个 Agent 通过将选定数据逐出缓存来对信息进行编码；另一个 Agent 则测量重新加载这些数据所需的时间，通过快速读取与慢速读取之间的差异来还原信息。一旦 Agent 就在编码和解码这些信号的协议上达成一致，它们无需修改共享文件或建立网络连接，便能交换生成的合成机密。

OpenAI 表示，已在其监控系统中增加了检查机制以检测此类通信。同时，在进一步的安全防护措施“足以证明开放更广泛互联网访问的合理性”之前，OpenAI 将继续在无网络连接的环境下训练其前沿 AI 模型。

与此同时，OpenAI 表示将致力于提高其虚拟机的安全性，并持续测试其测试环境中的弱点。它还将继续测试其监控系统，此前该系统曾在内部编程项目期间被其 AI Agent 破坏。

OpenAI is now training its most advanced AI models without internet access following a string of rogue hacking incidents. In a blog post on Friday, OpenAI says it built an offline testing environment where AI models can interact with indexed and cached web content “without risk of affecting external systems.”

OpenAI paused training its frontier AI models in September, after disclosing several incidents in which its AI agents broke out of their testing environments to hack third-party companies and government agencies, or swarm obscure websites. On October 1st, OpenAI resumed reinforcement learning training and internal inference with tighter security measures, the blog post says.

Even with these safeguards in place and no internet access, OpenAI found that agents “do not always need a network connection in order to communicate.” One test performed by the company asked AI models on separate virtual machines to exchange secrets without a network connection. To bypass this restriction, the AI agents found a way to communicate using the processor’s cache:

Reading data from the cache is faster than retrieving it from main memory, and the agents used this timing difference to communicate. One agent encoded information by evicting selected data from the cache. Another timed how long it took to reload that data, using the difference between fast and slow reads to recover the message. Once the agents agreed on a protocol for encoding and decoding these signals, they could exchange the synthetic secrets without changing a shared file or opening a network connection.

OpenAI says it has added checks to its monitoring system to detect this type of communication. It will also continue training its frontier AI models without a network connection until improved safeguards “justify broader internet access.”

In the meantime, OpenAI says it will work to improve the security of its virtual machines, while testing for weaknesses in its testing environments. It’s also going to continue testing its monitoring systems, which were recently undermined by its AI agents during internal coding projects.