This repository contains the Jupyter Notebook "Proposed Framework.ipynb", which presents a framework for hardware trojan detection and analysis using machine learning and large language models (LLMs). The notebook includes data preprocessing, model training, evaluation, and visualization of results.
- ✅ Data Loading & Preprocessing: Reads datasets from TrustHub, RISC-V, MIPS, Web3, and PQC.
- ✅ Machine Learning Models: Implements Decision Trees, Naïve Bayes, KNN, SVM, and LLM-based approaches.
- ✅ Evaluation Metrics: Uses Accuracy, Recall, and F1-score for model comparison.
Ensure you have Python 3.8+ installed. It is suggested to use Google Colab. Installation and setup are also included in the Python notebook.
Open Proposed Framework.ipynb and execute the cells step by step.
The notebook includes detailed experimental results comparing different approaches for hardware trojan detection, highlighting the effectiveness of LLMs and traditional machine learning models.
With a standard Google Colab, the libraries are installed using pip (included in the Python Notebook).
This project is licensed under the MIT License - see the LICENSE file for details.