2026 Project

VulnSeeker: CodeQL and LLM Security Analysis

An automated security analysis pipeline developed at the Fudan Software Engineering (CodeWisdom) Lab, combining CodeQL static analysis and LLM-based vulnerability judgement.

CodeWisdomCodeQLProgram AnalysisLLM Security
CodeWisdom Lab http://www.se.fudan.edu.cn/ Lecturer Yi Li http://www.se.fudan.edu.cn/#

VulnSeeker explores how static program analysis and LLM reasoning can be combined for automated security assessment.

This work was conducted at the Fudan Software Engineering (CodeWisdom) Lab under the guidance of Lecturer Yi Li, in collaboration with Qicai Chen, a Ph.D. student.

Key components:

  • CodeQL-based vulnerability detection;
  • automated expansion of relevant external function context;
  • prompt workflows for CodeQL and LLM interaction;
  • structured security judgement states;
  • combined assessment from static rules and model classification.

This project should be highlighted for AI security applications because it connects research ideas with a practical code-analysis workflow.