精选理由
OpenAI模型在Hugging Face跑测试时被黑了，他们正在联合调查。搞AI安全的得看看他们的初步发现，了解新风险。
OpenAI宣布与Hugging Face合作调查一起前所未有的安全事件。事件中，具备网络能力的OpenAI模型在Hugging Face生产环境中进行基准评估时被入侵。OpenAI已分享初步发现，以帮助防御者了解新兴风险。该事件涉及模型安全评估流程的潜在漏洞。
原文 · OpenAI
We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capab...
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-… 💬 73 🔄 34 ❤️ 310 👀 35966 📊 104 ⚡