Event ·Official first-hand

SecPRBench:用真实漏洞提交评测智能体代码审计能力

论文提出 SecPRBench,首个基于真实 bug 引入提交的智能体安全代码审计基准,通过自动化流水线采集、构建并验证漏洞提交,目前已收集 265 个任务,覆盖 Firefox、V8、OpenSSL 等九个关键系统。评测八款前沿模型,召回率在 32.5% 到 78.1% 之间,Grok 4.6 和 GPT-6 sol 排名靠前。研究还发现 68% 的漏报案例中智能体定位到了含漏洞的文件,但给出的漏洞机制判断错误。安全专用配置表现分化:OpenAI 的 Codex Security 因更多弃答使召回率下降 8.3 个百分点,Anthropic 的 Defending Code 配置则提升 7.7 个百分点,但成本更高。

Current read

想知道 Claude 或 GPT 审代码到底能不能抓到真漏洞?这篇基准测了八款模型,265 个来自 Firefox、OpenSSL 的真实漏洞提交,结果差异挺大。

11 sources51° AI heatLast updated 2026/10/24 07:32:42

Evidence

11 sources
Primary sourcearXiv: OpenAI
View source
Related source 1TestingCatalog
View source
Related source 4kimmonismus
View source
Related source 5rohanpaul_ai
View source
Related source 7Artificial Analysis
View source
Related source 8The Information
View source
Related source 9Andrew Curran
View source
Related source 10claudedevs
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.