Triplet Learning for Cross-Version Smart Contract Vulnerability Detection

This repository contains the code implementation and datasets for the paper titled: “Triplet Learning for Cross-Version Smart Contract Vulnerability Detection.” The code is designed to be executed on Google Colab for optimal reproducibility. We highly recommend running the code in Colab to avoid potential compatibility issues.

• Python 3.x
• torch
• transformers
• tensorflow
• keras
• tree_sitter
• scikit-learn

To install the required packages, follow these steps:

1. Install the additional packages using pip: !pip install torch !pip install transformers !pip install tensorflow !pip install keras !pip install tree_sitter !pip install scikit-learn

To use this code, follow these steps:

1. Clone this repository: !git clone https://github.com/chansuixi/Triplet_Detection.git
2. Navigate to the repository directory, such as: %cd drive/MyDrive/Triplet-Detection
3. Open the detect.py file in Colab and execute the code cells to start the detection process: !python detect.py