Transformer-Based Malware Detection Using Process Resource Utilization Metrics project on Python

Transformer-Based Malware Detection Using Process Resource Utilization Metrics project abstract

Transformer-Based Malware Detection Using Process Resource Utilization Metrics project description

This project proposes a web-based malware detection system developed using the MERN stack with a Python-based machine learning backend. The frontend is built using React.js to provide an interactive and responsive user interface, while the backend services are handled using Node.js and Python. The system analyzes process resource utilization metrics such as CPU usage, memory consumption, disk activity, and runtime behavior to detect malicious software. A Transformer-based deep learning model is used to learn temporal patterns in system behavior and accurately classify malware and benign applications. The application includes secure authentication, file upload functionality, real-time analysis dashboards, and detailed malware detection reports, making it effective for detecting modern and zero-day malware threats

Project Modules

The User Module includes a secure Login Page that allows users to register, log in, log out, and manage their passwords. After successful login, users can access the malware detection dashboard, upload files or datasets for analysis, and submit them for scanning. The system displays results such as malware or benign status, confidence score, and risk level. Users can also view detailed analysis reports, track previous scan history, and interact with visual dashboards. This module ensures secure access, smooth user experience, and effective interaction with the malware detection system.

Software Requirements

The system requires an operating system such as Windows, Linux, or macOS for development and execution. The frontend is developed using React.js with HTML, CSS, Bootstrap, and JavaScript. Backend services require Python with Flask or FastAPI for machine learning model integration and Node.js with Express.js for API handling. MongoDB is used as the database for storing user information and scan history. Additional software includes Python libraries such as NumPy, Pandas, PyTorch, and psutil, along with a modern web browser like Google Chrome or Firefox.

Hardware Requirements

The system requires a computer with a minimum Intel i5 or equivalent processor to handle malware analysis tasks efficiently. At least 8 GB RAM is recommended for smooth execution of machine learning models and backend services. A minimum of 50 GB free disk space is required for storing datasets, logs, and application files. Stable internet connectivity is needed for web access and updates. Optional GPU support can improve model training performance but is not mandatory for deployment.