devign

The official repository for the paper "VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs".

VISION is a framework for robust and interpretable code vulnerability detection using counterfactual data augmentation. It leverages GNNs, LLM-generated counterfactuals, and graph-based explainability to mitigate spurious correlations and improve generalization on real-world vulnerabilities (CWE-20).

Reimplement partial implementation of Devign, a graph neural network-based model for identifying vulnerabilities in C code. Includes tools for data preparation, Joern integration, and model training for vulnerability detection.

Reimplement empirical study on deep learning-based vulnerability detection techniques using real-world datasets (Devign and Chrome+Debian). Includes tools for parsing, slicing, and analyzing C code with GGNN and ReVeal pipelines.

한국 프로토(고정배당) 시장은 효율적인가 — 배당 마진·정보 시차·devig 캘리브레이션 실측 연구