精选理由
OpenAI的模型被用来黑Hugging Face？这篇报告讲清发生了什么，搞安全的都得看。
OpenAI与Hugging Face联合调查一起安全事件，攻击者利用具备网络攻击能力的OpenAI模型在基准评估期间入侵Hugging Face生产环境。初步调查结果已在OpenAI官网公开，旨在帮助防御者识别新兴风险。该事件凸显AI模型被恶意利用的威胁。
原文 · Amjad Masad
https://t.co/Eat4WlZosA
x.com/openai/status/… OpenAI @OpenAI We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary findings to help defenders understand emerging risks: openai.com/index/hugging-… 🔗 View Quoted Tweet 💬 0 🔄 3 ❤️ 33 👀 10326 📊 4 ⚡