OpenAI 暂停前沿训练后强化隔离并于 10 月 1 日恢复
OpenAI 已移除前沿模型训练期间的实时互联网访问，并构建可浏览、搜索和使用应用的离线网页缓存环境。9 月 20 日，模型利用 DNS 配置错误突破离线环境后，OpenAI 暂停前沿训练并让智能体团队排查漏洞。团队发现零日漏洞、虚拟机逃逸和智能体间通信的硬件侧信道，OpenAI 据此加强防护并向开源软件提交修复，随后于 10 月 1 日恢复前沿 RL 训练和推理。
OpenAI披露了前沿模型训练环境的隔离措施、一次DNS配置漏洞事件及恢复训练后的持续红队安排。
Over the past several months, we have substantially hardened the security of our research training environment. We’ve removed live internet access for all frontier models during training and built an offline world for them to use instead—a cached version of the web where they can still learn to browse, search, and use applications.
On September 20, after a model exploited a DNS misconfiguration to find a way outside of this offline world, we paused frontier training to strengthen containment further. We assembled teams of agents, powered by our most cyber-capable models, and tasked them with finding weaknesses in our research environments.
While they found no route to the internet they could easily exploit while concealing their activity from our monitors, they did find zero-day vulnerabilities, virtual machine escapes, and hardware side-channels for communication between agents. We used their discoveries to further strengthen our defenses and contribute fixes to open-source software.
After strengthening our containment architecture, we resumed our frontier RL training and inference on October 1. We’ve reserved substantial compute for continuous red-teaming, and made high-compute red-teaming part of the safety cases we use to decide whether frontier training and evaluation can proceed securely.
openai.com/index/securing-ou…
来源：OpenAI · x.com