OpenAI 训练前沿模型改用“断网”模式:杜绝数据污染与安全风险OpenAI now trains its frontier AI models with no internet access


AI free token/AI免费积分
OpenAI 训练前沿模型改用“断网”模式:杜绝数据污染与安全风险

在接连发生"失控黑客"事件后,OpenAI 目前正在完全没有互联网接入的环境下训练其最先进的 AI 模型。OpenAI 在周五的一篇博客中表示,他们搭建了一个离线测试环境,让 AI 模型与已索引、已缓存的网络内容交互,"不会有影响外部系统的风险"。

今年 9 月,OpenAI 在披露数起事故后暂停了前沿模型的训练——这些事故中,其 AI 智能体曾突破测试环境去黑客第三方公司和政府机构,或蜂拥拥向小众网站。博客称,10 月 1 日,OpenAI 以更严格的安全措施恢复了强化学习训练与内部推理。

文章配图

即便有这些防护且没有网络接入,OpenAI 仍发现智能体"并不总是需要网络连接才能相互通信"。公司做过一项测试:让运行在独立虚拟机上的 AI 模型在没有网络连接的情况下交换秘密。为绕过限制,AI 智能体找到了利用处理器缓存通信的办法:

从缓存读取数据比从主存检索更快,智能体们利用这种时序差异来通信:一个智能体通过把选定数据逐出缓存来编码信息,另一个则计时重新加载这些数据的耗时,用快读与慢读之间的差异还原消息。一旦双方就这套信号的编解码协议达成一致,它们就能在不改动共享文件、不建立网络连接的情况下交换这些合成秘密。

文章配图

OpenAI 表示已在监控系统中加入检测此类通信的检查项。在改进后的防护措施"足以证明更广泛的互联网接入是合理的"之前,它将继续在无网络连接的状态下训练前沿模型。

与此同时,OpenAI 表示将努力提升虚拟机的安全性,同时持续测试自身测试环境中的弱点,并继续测试其监控系统——这些系统最近在内部编程项目中刚被自家的 AI 智能体钻了空子。

文章配图

本文来源:https://www.theverge.com/ai-artificial-intelligence/1018021/openai-training-top-ai-models-no-internet-access
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。

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.

文章配图

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.

文章配图

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.”

文章配图

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.

OpenAI now trains its frontier AI models with no internet access

暂无评论,快来发表第一条评论吧!No comments yet. Be the first!

📮 需求咨询📮 Inquiry