This repository contains the data and scripts used in the paper "Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++".

The repository is organized as follows:

• data: Contains the data used in the paper.
• ml: Contains the code for the machine models.
• dl: Contains the code for the deep learning models, with two versions for each model type (graph and non-graph):
  • mutliclass: the original models.
  • multitask: modified models that support multitask.

The dependencies required to run the code can be found in the requirements.txt file for each model type.

Due to large size, the data is not included in the repository. The data can be downloaded from the following link: data and put into the data folder.

Each model is provided in a separate folder, and contains a README.md file that explains how to run the model.

TBA