🚀 Project Name :

PE Malware Detection - Portable Executable Malware Detection Using Machine Learning

📌 Project Overview :

Portable Executable Malware Detection leverages machine learning to identify benign and malicious PE files. This system analyzes a dataset of PE files and uses various features to train a model that detects malware with high accuracy. The goal is to enhance cybersecurity by providing a reliable automated solution for malware detection.

🙏 Project Member :

• 64102080 จิรกิตติ์ เอียดเหตุ
• 64125735 ธนวัฒน์ กองสีสังข์

📊 Dataset :

The dataset used for training the machine learning model is the Benign & Malicious PE Files, which contains a total of 19,611 entries and 79 features. This comprehensive dataset is essential for training a reliable malware detection system.

🧠 Conceptual Framework :

Here is the conceptual framework that outlines the steps in the detection process:

🎯 Objective :

• Select the most relevant features for building an accurate malware detection model for PE files.
• Develop a machine learning-based tool to classify PE files as benign or malicious.

✨ Key Features :

• Feature Selection & Extraction – Identify important features from PE files to improve model performance.
• Machine Learning Model Training – Train and test different algorithms to find the best model for detection.
• Real-Time Malware Classification – Analyze and classify PE files as benign or malicious.
• Command-Line Interface (CLI) – Simple and efficient command-line tool for quick scanning.
• High Accuracy Detection – Optimized model to minimize false positives and false negatives.

🛠 Tech Stack :

• Programming Language: Python
• Libraries: Scikit-learn, Pandas, NumPy, PEfile
• Machine Learning Models: Random Forest, multilayer perceptron (MLP), k-nearest neighbors (KNN)
• Deployment: Local Execution

📂 GitHub Repository (Source Code) :

• https://github.com/TOEYJIRAKID/Malware-Detection-Using-ML

⚙️ Installation & Setup :

1. Clone the repository

   git clone https://github.com/TOEYJIRAKID/Malware-Detection-Using-ML.git

2. Run the Malware Detection Command

   python main.py <model.pkl> <pe_file>

3. This command will load the trained model and detect whether the provided PE file is benign or malicious.

📽️ Project Preview :