.png){kind=icon}
.png){kind=icon}
Return
Enhancing static vulnerability alert validation using large language models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jss.2026.113040.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A hybrid framework combining SAST, CPG, and LLM for vulnerability validation. • Utilizes CPG as a structural anchor to ground LLM reasoning for higher accuracy. • Reduces false-positive SAST alerts through evidence-grounded LLM adjudication.
Journal
IF:
4.1
Papers:
5.4K
Citations:
8.4K