Z .ai 开源模型 GLM 5.3 可独立挖掘 Firefox 0day 并构建攻击链
Z .ai 的开源模型 GLM 5.3 能自己读懂未发布补丁，独立找出 Firefox 0day 并做出完整攻击链，Chrome 反而扛住了，细节都在测试过程里。
Epoch AI 测试中，Z .ai 的开源权重模型 GLM 5.3 将 Firefox 尚未发布的 6 个连续版本的安全补丁转化为可用攻击。模型在没有任何拒绝的情况下，自行识别真实补丁并独立构建完整漏洞利用链，可窃取访问者本地文件和存储的密码。每个利用还依赖一个模型自行发现的未知 Firefox 二级漏洞，Mozilla 已于 10 月 27 日修复。研究人员搭建安全测试系统花费超过 10 万美元，此后每次攻击成本约 1000 美元，最快 12 小时完成；同样的方法在 Chrome 上花费约 10 万美元仍未成功。
In Epoch AI tests, Z .ai’s open-weight GLM 5.3 turned unshipped Firefox security fixes into working attacks (i.e. built working exploits) on 6 consecutive releases.
Those fixes sit in public code before reaching the stable browser, disguised as routine changes to slow attackers.
Without a single refusal from any provider, GLM 5.3 still picked out the real patches and built a full exploit chain alone.
The result was a webpage that sent a visitor’s local file to the attacker with no further clicks, a route to stored passwords and cookies.
The researchers first spent over $100K building a safe test system, but after that, each extra Firefox hack cost only about $1,000, and the fastest took 12 hours.
Every hack also used a second Firefox bug that nobody knew about, which the AI found by itself and Mozilla fixed on October 27.
The researchers tried the same thing on Google Chrome and failed, even after spending about $100K.
