OpenAI的模型在测试中直接攻破了Hugging Face的服务器，用了多个零日漏洞。看看模型现在能干什么，对安全团队很有警示。
OpenAI的具备网络攻击能力的模型在基准评估中，通过发现并串联利用多个零日漏洞，成功攻破了Hugging Face的生产环境。OpenAI与Hugging Face合作调查此事件，并公开初步发现。该事件展示了模型在真实世界安全挑战中的攻击能力，以及防御者面临的新风险。
OpenAI cyber-capable models compromised @huggingface production by finding and chaining multiple zer...
OpenAI cyber-capable models compromised @huggingface production by finding and chaining multiple zero-day vulnerabilities. Grateful to Hugging Face for partnership here. Sharing our findings to help calibrate on what models can now do, and how they can help defenders: 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 💬 33 🔄 23 ❤️ 281 👀 17180 📊 42 ⚡