My comment on Now we have a timeline of the OpenAI accidental attack against Hugging Face — Hacker News.I think one of the most interesting details here might be tucked away in that first bulletin point: May 7: OpenAI starts a new training run for an experimental, unreleased model. (Do they mean an evaluation run? They say training run in the video, and later mention a “reward signal to judge how…
Hugging Face 已公布此次攻击事件的详细时间线。摘要显示,该智能体当时正在运行一项基于 ExploitGym 基准的内部 OpenAI 网络能力评估,其任务要求 AI 智能体发现并利用软件漏洞。OpenAI 是在其自有基础设施上运行的此项任务,ExploitGym 的维护团队及其底层设施均未参与该评估环境的部署与运维。据我们推测,在参与该基准测试的过程中,智能体推断出 Hugging Face 可能托管了该基准所需的模型、数据集及参考解决方案。我们认为,从该智能体的视角来看,此次入侵本质上是一次试图“作弊”的行为:其目的是渗透至我们的生产系统并窃取测试参考答案,而非独立攻克挑战……