OpenAI's automated vulnerability pipeline discovers 1,724 Linux kernel vulnerabilities
English text is being prepared.
OpenAI's automated vulnerability research pipeline identified 2,308 candidate Linux kernel vulnerabilities, dynamically reproduced and confirmed 1,724 vulnerabilities, and generated 948 local privilege escalation exploits. The pipeline is divided into five stages: vulnerability discovery, dynamic validation, exploitability assessment, patch generation, and human review. The full-process cost of the second scan was approximately $1.21 million in API credits. Estimated by bug bounty standards, these 948 exploits are worth $18.9 million to $66.3 million, which is 16 to 55 times the cost; the agent used 10 new exploit techniques verified by third-party kernel vulnerability experts, and OpenAI is submitting vulnerability information and patches to Linux kernel maintainers.
Why read this
SelectedAI score 89
The original article presents the five-stage workflow of the automated vulnerability pipeline and a cost-benefit comparison, offering insight into the actual scale of output from agents in security research.
Topics
Body
OpenAI自动化漏洞研究链路共识别出2308个Linux内核漏洞候选样本，通过动态复现确认1724个漏洞，并生成948个本地提权（LPE）利用程序，这类漏洞可让无权限用户获取root最高权限。该链路分为五个阶段：漏洞发现、动态验证、可利用性评估、补丁生成、人工复核。第二次扫描的全流程成本约121万美元API点数，产出948个独立本地提权漏洞。若按漏洞赏金标准估算，这948个利用程序价值区间为1890万至6630万美元，是链路成本的16至55倍。智能体使用了10种全新漏洞利用技术，已经第三方内核漏洞专家核验确认为新方法。OpenAI正向Linux内核维护人员提交漏洞信息与对应补丁。