The writer is co-founder and chief science officer of Hugging Face
本文作者是Hugging Face联合创始人和首席科学官
It wasn’t until late in the afternoon on Saturday July 11 that the team at Hugging Face realised something was wrong. This was the final day of the International Conference on Machine Learning in Seoul and a few days before school summer holidays started, meaning our security and research teams were scattered all over the world. I was working from the Netherlands.
一直到7月11日（周六）下午晚些时候，Hugging Face的团队才意识到出了问题。那是首尔国际机器学习大会(International Conference on Machine Learning)的最后一天，而中小学即将开始放暑假，这意味着我们的安全和研究团队分散在世界各地。我本人当时在荷兰远程工作。
Just before 2pm GMT a series of “UnauthorizedAccess” and “PrivilegeEscalation” alerts started to appear on our monitoring tools. Appropriated credentials used to access the system had triggered detection warnings. One of our security engineers posted a prescient message on our Slack channel: “looks like a LLM [large language model] attack to me.”
格林尼治标准时间(GMT)下午快到2点的时候，我们的监测工具上开始出现一连串“未经授权访问”(UnauthorizedAccess)和“权限提升”(PrivilegeEscalation)警报。触发这些探测警报的是被盗凭证被用来访问系统。我们的一位安全工程师当时在我们的Slack频道上发布一个颇有先见之明的帖子：“在我看来，这像是一次LLM（大型语言模型）攻击。”