Epoch AI 的实验发现，GLM-5.3 能利用安全修复已公开但尚未推送给用户的补丁空窗期，自主攻破近期多个 Mozilla Firefox 版本。在仅给出基础指令的情况下，模型为六个近期 Firefox 版本独立构建出可用漏洞利用，每个版本成本约 1000 美元，最快一次仅用 12 小时；攻击可让用户在打开单个网页后泄露浏览器保存的密码、认证 cookie 或读取本机文件。作者称模型还独立发现并利用了一个此前未公开的漏洞，已通报 Mozilla，后者在 10 月 27 日发布的 Firefox 159.0 中完成修复。
Epoch AI 的实验显示开源权重模型能在补丁窗口内自主构造浏览器漏洞利用，成本约每版本 1000 美元。
GLM-5.3 can exploit the period between a security fix becoming publicly available and the fix reaching end users (the patch gap)
by analyzing the security fixes it can reverse engineer the underlying vulnerabilities and develop working exploits before users receive the patches
【引用 @EpochAIResearch】In recent experiments, we found that GLM 5.3 can autonomously compromise recent versions of Mozilla Firefox using security fixes that have been published but not yet shipped to users.
We used a deliberately basic setup meant to emulate a relatively unsophisticated attacker with limited resources. After basic initial instructions to inspect those not-yet-shipped fixes, the model reliably built successful exploits for six recent Firefox versions on its own using only information available at the time of release.
These exploits, which cost about $1,000 per compromised version, would let an attacker steal passwords and authentication cookies stored in the browser, or read any files on the user's computer, after the user opens a single webpage, with no further interaction.
The exploits make use of the "patch gap," the time between when security fixes are made public in beta or "nightly" software updates and when those fixes are generally released to users. Until now, exploiting it required significant human time and skill, or special access to frontier models with advanced cyber capabilities.
Our results show that widely available open-weight models can now do this relatively cheaply and quickly. We gave GLM 5.3 up to 48 hours to find an exploit, but its fastest attempt needed only 12 hours.
In all of its successful attacks, the patch gap gave GLM 5.3 an initial foothold in the browser. To turn that foothold into reading files off the user's computer, the model also independently discovered and used a previously unpublished vulnerability.
We shared our findings with Mozilla, which patched the vulnerability in its October 27 Firefox 159.0 release. We haven't yet confirmed whether the attack still succeeds without it, but expect the fix makes it substantially harder. We're grateful to Mozilla for their responsiveness and collaboration.
In recent experiments, we found that GLM 5.3 can autonomously compromise recent versions of Mozilla Firefox using security fixes that have been published but not yet shipped to users. We used a deliberately basic setup meant to emulate a relatively unsophisticated attacker with limited resources. After basic initial instructions to inspect those not-yet-shipped fixes, the model reliably built successful exploits for six recent Firefox versions on its own using only information available at the time of release. These exploits, which cost about $1,000 per compromised version, would let an attacker steal passwords and authentication cookies stored in the browser, or read any files on the user's computer, after the user opens a single webpage, with no further interaction. The exploits make use of the "patch gap," the time between when security fixes are made public in beta or "nightly" software updates and when those fixes are generally released to users. Until now, exploiting it required significant human time and skill, or special access to frontier models with advanced cyber capabilities. Our results show that widely available open-weight models can now do this relatively cheaply and quickly. We gave GLM 5.3 up to 48 hours to find an exploit, but its fastest attempt needed only 12 hours. In all of its successful attacks, the patch gap gave GLM 5.3 an initial foothold in the browser. To turn that foothold into reading files off the user's computer, the model also independently discovered and used a previously unpublished vulnerability. We shared our findings with Mozilla, which patched the vulnerability in its October 27 Firefox 159.0 release. We haven't yet confirmed whether the attack still succeeds without it, but expect the fix makes it substantially harder. We're grateful to Mozilla for their responsiveness and collaboration.在 X 查看被引用的帖子
来源：Lisan al Gaib · x.com