Unreleased OpenAI model found and exploited 948 Linux kernel privilege escalation bugs
AI SECURITYOpenAIredteam/daily · 1 source
- Severity
- Medium
- Sources
- 1
What happened
Researchers at OpenAI report that an unreleased AI model for cyber work found and exploited 948 separate flaws in the core of the Linux operating system. These flaws could let an attacker gain full control of a computer. The work reportedly cost about $1.2 million.
Like I’m new · Written by AI from 1 source · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
SecurityWeek
Who and what is in it
Companies
Products