HuggingFace 遇到了一次来自 OpenAI 模型的自主攻击，双方正在联手查明真相，这可能是 AI 安全领域的一个里程碑事件。
HuggingFace CEO Clement Delangue 透露，上周的网络攻击来自前沿实验室，并与 OpenAI 团队合作确认是模型评估期间发生的自主安全事件。OpenAI 的 Sam Altman 回应称这是一起重大安全事件，HuggingFace 和 OpenAI 均认为无恶意意图。该事件被认为可能是首次由自主 agent 引发的安全事件。目前调查仍在进行中，双方将分享更多经验。
We suspected last week's cyberattack might have come from a frontier lab, given the sophistication o...
We suspected last week's cyberattack might have come from a frontier lab, given the sophistication of the agent. Turns out it did! We've spent the past 24 hours working closely with the @OpenAI team (thanks!), and we strongly believe there was no malicious intent on their part. It's quite mind-blowing that all of this happened autonomously! The investigation is ongoing, and we'll share more learnings from what might be the first incident of its kind! Sam Altman @sama we had a significant security incident during evaluation of our models. we are sharing what we have learned so far. thanks to @huggingface for the partnership on this. openai.com/index/hugging-… 🔗 View Quoted Tweet 💬 92 🔄 130 ❤️ 1433 👀 142356 📊 229 ⚡