This project is an implementation of a novel approach to detect vulnerabilities in source code. The approach consists of first extracting the graphical representation of source code, then creating a mixed representation of the three most important representations AST, CFG, and PDG, then benchmarking the performance of every combination with a graphical neural network.
- Clone the repo
git clone https://github.com/maykel-mattar/vulnerability-detection.git
- Compose the docker containers
docker-compose up
- Open the vulAPC notebook and give it a try!
Maykel Mattar - maykel.mattar@univ-ubs.fr
Project Link: https://github.com/maykel-mattar/vulnerability-detection