GLM 5.3 零人工干预48小时内构建完整Firefox漏洞利用链
原标题：Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours
AI 摘要
Epoch AI 研究人员展示，开源权重模型 GLM 5.3 在无人工干预下，于 48 小时内自主构建出针对 Firefox 的完整漏洞利用链，利用补丁公开到用户更新之间的“补丁空窗期”，在 6 个 Firefox 版本上成功实现攻击，每次攻击 API 成本约 1000 美元。该模型识破了 Mozilla 将安全修复伪装成常规改进的做法，并独立发现一个此前未知漏洞以绕过沙箱读取本地文件。研究团队已向 Mozilla 披露，漏洞在 Firefox 159.0 中修复；他们警告补丁空窗风险遍及整个软件行业，且对 Chrome 的同类尝试花费约 10 万美元未获成功。
正文节选
Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours Key Points - Epoch AI researchers showed that the widely available AI model GLM 5.3 can autonomously exploit Firefox before publicly visible security fixes reach users. - The model identified disguised security fixes and chained vulnerabilities with a previously unpublished flaw to bypass browser protections and read local files when a user simply visited a webpage. - Once the test setup was in pl