https://github.com/Boshra-01/Rust-IR-BERT

https://github.com/Boshra-01/Rust-IR-BERT

Last synced: 30 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/Boshra-01/Rust-IR-BERT
• Owner: Boshra-01
• Created: 2025-05-24T05:06:06.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-05-24T05:17:15.000Z (about 1 year ago)
• Last Synced: 2025-05-24T05:27:01.049Z (about 1 year ago)
• Language: Jupyter Notebook
• Size: 0 Bytes
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Rust-Checker - Rust-IR-BERT - Based Vulnerability Detection in Rust Code Using LLVM IR and Transformer Model. Paper: [Machine Learning and Knowledge Extraction](https://www.mdpi.com/2504-4990/7/3/79) | Source Code, LLVM IR | Vulnerabilities | BERT | 2026-10-20 | (Static Checkers)

README

          
# Rust-IR-BERT 

## Machine Learning-Based Vulnerability Detection in Rust Code Using LLVM IR and Transformer Model

This repository implements **Rust-IR-BERT**, a machine-learning pipeline for automated vulnerability detection in Rust code. It provides the following two end-to-end workflows:

- **LLVM IR Pipeline**  

  1. Compile Rust source to LLVM IR  

  2. Extract semantic embeddings with GraphCodeBERT  

  3. Classify vulnerabilities using CatBoost  

- **Rust Source Pipeline**  

  1. Clean and tokenize raw `.rs` files  

  2. Extract embeddings with GraphCodeBERT  

  3. Classify with CatBoost