Vulnerability Mining

The paper constructs a source code snippets vulnerability mining system named PyVul based on deep learning to automatically detect the security of code snippets in the open source community.

This project studies the security of source code fragments in open source communities, extracts the core code associated with vulnerabilities through program slicing techniques, and constructs a BiLSTM model for malicious code detection. The text features of posts are also constructed using TF-IDF to train OVO SVMs models for vulnerability code type identification.