OpenAI publishes research on automatic Linux vulnerability discovery and patching
What happened
On November 4, OpenAI published Linux kernel vulnerability research and built a pipeline that autonomously finds vulnerabilities, generates exploits and drafts candidate patches. The run dynamically reproduced 1,724 vulnerabilities, confirmed 948 unique local privilege escalation flaws and produced candidate patches. Total API cost was $1,213,430, or $1,279 per local privilege escalation exploit on average. The pipeline used an unreleased cybersecurity model, and results went to maintainers after human review; hundreds of severe vulnerability reports and patches have been sent so far.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- OpenAI NewsPickOpenAI details Linux kernel bug hunt: 948 local privilege-escalation flaws confirmed, patches generated
OpenAI built a pipeline that finds, exploits and patches vulnerabilities on its own. In Linux kernel research it confirmed 948 unique local privilege-escalation bugs and produced candidate patches, dynamically reproducing 1,724 vulnerabilities at a total API cost of $1,213,430, or $1,279 per local privilege-escalation exploit on average. The pipeline uses a cybersecurity model OpenAI has not yet released; results went to maintainers after human review, and hundreds of severe bug reports and patches have been sent out.
Heat over time
Not enough continuous observations to draw a trend yet.