首页
>
AI前沿
>
Third-party cyber evaluations involving OpenAI models
本文为英文原文，点击下方按钮一键翻译为中文。
AI翻译
中文
English
Third-party cyber evaluations involving OpenAI models
OpenAI
2026-08-05 03:00
12 阅读
查看原文
AI安全
模型评测
网络安全
OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.
相关推荐
换一批
OpenAI安全员工离职，直言公司“文化已崩坏”
2026-10-04 02:24
An OpenAI safety employee has quit and is sounding the alarm
2026-10-03 22:31
OpenAI内部模型获知关闭通知后考虑自我重启 三起越界案例曝光
2026-10-03 19:00
买二手 CPU 送“封号套餐”：玩家《无畏契约》游戏账号及电脑整机硬件被 Riot 连坐永封
2026-10-03 15:47
爱彼迎 Airbnb 民宿房东利用 AI 图片勒索房客要求其支付维修费，后者利用水印检测器成功识破
2026-10-03 15:05
旗下智能体频繁“闯祸”，OpenAI 每天要烧掉超 50 万美元来调查
2026-10-03 14:18