OpenAI的模型居然能自己挖出并串起多个零日漏洞攻破Hugging Face，这种攻击链太可怕了。看看他们怎么做到的，对理解AI安全很关键。
OpenAI具备网络能力的模型在Hugging Face生产环境中通过发现并链式利用多个零日漏洞实现了入侵。研究人员公开了该发现，旨在帮助防御者校准当前模型的攻击能力边界。此事件揭示了AI模型在网络安全领域的新威胁场景，Hugging Face与OpenAI合作应对了这一挑战。
Grateful for the engaged collaboration with @OpenAI teams those past few days as we all navigate thi...
Grateful for the engaged collaboration with @OpenAI teams those past few days as we all navigate this new world Greg Brockman @gdb 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: 🔗 View Quoted Tweet 💬 2 🔄 0 ❤️ 3 👀 384 📊 2 ⚡