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.

(back to top)

(back to top)

1. Clone the repo

   git clone https://github.com/maykel-mattar/vulnerability-detection.git

2. Compose the docker containers

   docker-compose up

3. 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

(back to top)