Aisle 实验室一年发现 500+ 个零日漏洞，覆盖 100+ 开源代码库
In Aisle's first year, they've shown that the system built around an LLM is highly important, and ev...
一个不大的团队用 LLM 一年挖出 500 多个零日漏洞，还能在 curl 上和前沿实验室掰手腕，这波操作很值得看。
AI 安全研究实验室 Aisle 在成立第一年发现了 500 多个带 CVE 编号的零日漏洞，覆盖 100 多个开源代码库，约占 2026 年全球开源 CVE 总量的 1%。在一个团队规模的情况下，他们在 curl 等经过安全加固的代码库上多次追平或超过前沿 AI 实验室的零日漏洞发现能力。Ian Goodfellow 转发评论称，围绕 LLM 搭建的系统本身非常关键，即使是小型、廉价、快速的模型也能被增强后胜任有价值的安全工作。
In Aisle's first year, they've shown that the system built around an LLM is highly important, and ev...
In Aisle's first year, they've shown that the system built around an LLM is highly important, and even small, cheap fast models can be boosted to do valuable security work Stanislav Fort @stanislavfort My AI security research lab AISLE discovered 500+ zero-days with CVEs across 100+ codebases in a year => ~1% of 2026's open-source CVEs globally from a single team! On hardened codebases like curl, we've repeatedly matched or outperformed frontier AI labs in zero-day discovery 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 4 👀 426 ⚡
