Skip to content
Hot eventLive

ObliVul:告警条件化安全义务建模与双向反事实验证框架

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv Software Engineering 刊登一手报道,介绍面向代码漏洞检测的 ObliVul 框架。该框架提出告警条件化安全义务建模与双向反事实验证方法:先从代码属性图(CPG)提取 Local Evidence Pack(LEP),再用大语言模型恢复候选安全义务,随后对齐程序节点、依赖边与路径范围,构建 Local Safety Obligation Graph(LSOG),最后由 VAFI 聚合证据,生成函数级漏洞预测。目前报道仅描述方法流程,未披露实验数据或开源信息。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Software Engineering
    ObliVul:面向代码漏洞检测的告警条件化安全义务建模与双向反事实验证

    ObliVul 提出告警条件化安全义务建模与双向反事实验证框架,用于代码漏洞检测。它先从代码属性图(CPG)提取 Local Evidence Pack(LEP),用大语言模型恢复候选安全义务,再对齐程序节点、依赖边与路径范围构建 Local Safety Obligation Graph(LSOG),最后由 VAFI 聚合证据生成函数级漏洞预测。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.