OpenAI uses a network vulnerability pipeline to discover and fix 948 local privilege escalation vulnerabilities in the Linux kernel.
OpenAI's security research team built an autonomous pipeline for discovering, exploiting, and patching network vulnerabilities. Using a forthcoming network model, they verified and generated patches in a single run, covering 948 local privilege escalation vulnerabilities in the Linux kernel. The total API cost was approximately $1.2 million, averaging about $1,000 per vulnerability. Funnel data shows that starting from 2,308 candidate findings, 1,724 passed verification, resulting in 948 usable LPE exploits and 291 usable PoCs.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original