OpenAI 用前沿网络安全模型一周发现约 1000 个 Linux 内核漏洞
additional context on the project: https://t.co/mDqbF3W0s3
OpenAI 拿自家前沿模型扫 Linux 内核，一周找到约 1000 个提权漏洞，人类一年才 20 个，这个数字对比很直观。
OpenAI 的 Eric Wallace 介绍，团队正将大量前沿算力投入开源代码库漏洞挖掘与修复，全部免费。以 Linux 内核为例，传统安全研究人员一年通常发现约 20 个本地提权（LPE）漏洞，而 OpenAI 即将推出的前沿网络安全模型在一周内用约 100 万美元的 token 找到了约 1000 个 LPE 漏洞。过程中该模型还发现了至少 10 类新的 Linux 漏洞利用技术。
additional context on the project: https://t.co/mDqbF3W0s3
additional context on the project: x.com/Eric_Wallace_/… Eric Wallace @Eric_Wallace_ We are now allocating a significant amount of our frontier compute towards discovering and patching vulnerabilities in open source codebases, fully pro bono. In one case, we studied the Linux kernel, which is a particularly load-bearing piece of software at OpenAI. Before AI, security researchers might discover ~20 local privilege escalation (LPE) vulnerabilities in Linux in a typical year. In one week's time, our upcoming frontier cyber model was able to find ~1000 LPE vulnerabilities using about $1M of tokens. In the process, it was able to discover at least 10 novel classes of Linux exploitation techniques. 🔗 View Quoted Tweet 💬 2 🔄 2 ❤️ 34 👀 5730 📊 4 ⚡
