# OpenAI Finds 948 Local Privilege Escalation Bugs In The Linux Kernel

DevFeed: [OpenAI Finds 948 Local Privilege Escalation Bugs In The Linux Kernel](<https://devfeed.tech/articles/openai-finds-948-local-privilege-escalation-bugs-in-the-linux-kernel-118791.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/OpenAI-948-Linux-LPE-Bugs>)

Author: Michael Larabel

Published: 2026-11-05T10:00:58Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [bugfixes](<https://devfeed.tech/topics/bugfixes.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api-credits](<https://devfeed.tech/tags/api-credits.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [formal-verification](<https://devfeed.tech/tags/formal-verification.md>), [frontier-models](<https://devfeed.tech/tags/frontier-models.md>), [gpt-5-5](<https://devfeed.tech/tags/gpt-5-5.md>), [gpt-5-5-cyber-model](<https://devfeed.tech/tags/gpt-5-5-cyber-model.md>), [gpt-5-6-sol](<https://devfeed.tech/tags/gpt-5-6-sol.md>), [hardening](<https://devfeed.tech/tags/hardening.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-kernel](<https://devfeed.tech/tags/linux-kernel.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [local-privilege-escalation](<https://devfeed.tech/tags/local-privilege-escalation.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [openai](<https://devfeed.tech/tags/openai.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [privilege-escalation](<https://devfeed.tech/tags/privilege-escalation.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability-discovery](<https://devfeed.tech/tags/vulnerability-discovery.md>)

## AI overview

OpenAI reports that its prototype identified 2,308 candidate Linux kernel vulnerabilities, dynamically reproduced 1,724, and found 948 local privilege escalation exploits that could let unprivileged local users gain root access. It also generated candidate patches for maintainer review. The work used $1.2 million in API credits. The researchers argue that as models become better at finding vulnerabilities and developing exploits, security efforts should include high assurance software, secure-by-default code, reducing unnecessary features, and formal verification. The supplied text also claims GPT-5.5 Cyber found more than five times as many novel LPEs as GPT-5.6 Sol, despite three months of kernel hardening and patches between scans.

## Source excerpt

OpenAI published a blog post outlining their work on autonomous vulnerability discovery. To showcase their AI potential, they found 948 valid local privilege escalation vulnerabilities within the Linux kernel...