Learning Algorithms to detect Vulnerabilities in Source Code

ML4Security
Code Embedding
NLP
Machine Learning

A project to detect key security vulnerabilities (buffer overflows, SQLi, etc.) in web application source code using a combination of static fuzzing and machine learning.
The project is sponsored by Hindustan Computers Limited (a Indian-based multinational IT services company).



Technologies Used: Python, Tensorflow, Java, Word Embedding.

My Role:
  • Designed the three-stream action recognition system.
  • Developed the frame buffer for real-time processing.
  • Neural Network pruning.

Project Gallery

fighting nazca boobies
SAST
otovalo waterfall
Comparison with other solutions