AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research
MentionsOpenAILinux kernel
An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million. The post AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research appeared first on SecurityWeek .
Summary from SecurityWeek.
Explained
The technology and terms in this story. Learn more
- TechnologyLinux kernelThe core of Linux and Android: it controls hardware, memory and what every program is allowed to do.
- AttackPrivilege escalationGoing from limited access to more powerful access, such as from a normal user to administrator.
- ConceptExploitCode or a technique that turns a software flaw into something an attacker can actually use.