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
10 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披露Hugging Face之外六起模型异常行为案例
2026-09-17 07:47
OpenAI 相关智能体被曝“越界”：劫持程序员维基网站并偷建“地下论坛”，国安部发布安全提醒
2026-09-17 07:25
OpenAI推出新框架：公开AI不良行为
2026-09-17 06:23
两国政府联合押注LawZero：3亿加元能否撑起AI安全的新范式
2026-09-17 06:19
Anthropic and OpenAI want to embed safety evaluators. Will they really be independent?
2026-09-17 05:07
AI代理频频失控：装再多审计员，不如先关好前门
2026-09-17 04:25