Skip to content
Hot storiesContinuously updated

OpenAI用AI系统挖掘并修复Linux内核提权漏洞

2 reports2 reporting sourcesUpdated 3 hours ago

Start here

AI overview

2026年11月4日，OpenAI官方公布其构建了一套自主流水线，实现了从漏洞检测、有效性验证到补丁代码生成的自动化全流程，在Linux内核中成功发现、验证并生成补丁修复了948个本地权限提升漏洞。11月5日发布的研究报告进一步显示，该自动化智能体系统在针对2,308个候选问题的检测中，成功复现了1,724个安全漏洞，并进一步针对这些漏洞生成了948个可实现本地提权的利用程序。

AI-generated from reports · Updated 3 hours ago

Latest developmentsNov 5 06:51
OpenAI发布报告披露AI复现1724个Linux内核漏洞并生成948个提权利用程序。

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. IT之家 · AI 筛选Selected
    OpenAI Releases Security Report: Scans Linux Kernel to Reproduce 1,724 Vulnerabilities and Generate 948 Privilege Escalation Exploits

    OpenAI has released a cybersecurity model research report detailing the use of an automated agent system to discover vulnerabilities in the Linux kernel, successfully reproducing 1,724 vulnerabilities out of 2,308 candidate issues and generating 948 exploits that achieve local privilege escalation.

Nov 4
  1. OpenAI 官方动态Selected
    OpenAI Builds Autonomous Pipeline to Discover and Patch 948 Linux Kernel Privilege Escalation Vulnerabilities

    OpenAI has built an autonomous pipeline that successfully discovered, validated, and generated patches for 948 local privilege escalation (LPE) vulnerabilities in the Linux kernel. The pipeline automates the entire end-to-end workflow, from vulnerability detection and validation to patch code generation.

Story heat trend

Not enough continuous data yet to draw a trend.