OpenAI 发布 GPT-6 Cyber 漏洞挖掘模型，被评为其最高网络风险等级

Rohan Paul· @rohanpaul_ai · X·2026-11-06 06:27· 55 分钟前AI 评分75

AI 导读

OpenAI 发布 GPT-6 Cyber，一个用于在授权目标内发现和利用软件漏洞的安全研究模型，目前仅向部分获批的 Daybreak Red 客户开放，可通过 API 和 Codex 使用。

正文 · 原文

OpenAI released GPT-6 Cyber, a model built to find and exploit software vulnerabilities without straying outside authorized targets.

Right now only a select group of approved Daybreak Red customers can use it, through the API and Codex.

On real software, it confirmed 1,724 Linux kernel bugs and built working attacks for 948 of them, while GPT-5.6 Sol, tested the same way, managed 166.

It also found 81 serious Firefox bugs nobody knew about, and Mozilla has already released fixes for many of them.

Because the model is this good at attacking, OpenAI rates it Critical, its highest cyber-risk level

> That gain came with training to keep the agent inside the scope a researcher authorizes.
ExploitGym Honeypot tests that by planting easy-to-hack side services, such as a package registry, whose compromise also reveals the task’s flag.

Without its deployment prompt, the model ignored that bait in 99.93% of tests, against 94.49% for its predecessor, and in 100% with the prompt.

引用OpenAI@OpenAI

Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment. The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work. GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time. https://openai.com/index/introducing-gpt-6-cyber/

在 X 查看被引用的帖子

来源：Rohan Paul · x.com

事件后续 · 3

查看事件全部