MALWARE DETECTION WITH MACHINE LEARNING METHODS BASED ON APPLICATION PROGRAMMING INTERFACE (API) CALLS

Overview

This repository contains resources and code for the research project "Malware Detection with Machine Learning Methods Based on Application Programming Interface (API) Calls" by Adnan Kutay Yüksel. The project aims to detect malware by utilizing machine learning techniques on Application Programming Interface (API) calls. The dataset used for this study is the API Malware Detection System (APIMDS) dataset.

Dataset

• The dataset used in this project can be accessed at APIMDS Dataset.
• Note: The dataset is not added to this repository due to its size (more than 25MB).

Feature List

• Features extracted from the dataset are provided in features.txt.

Input and Output Matrices

• Input Matrix: The input values used for training are stored in input_values.txt.
• Output Matrix: The labels corresponding to the input values are stored in output_values.txt.

Code

• The main code for malware detection is provided in malware_detection.py.

Result

• The accuracy obtained from executing the code is 98.04%.
• The result details are stored in result.txt.

Citation

If you use this code in your research, please cite the following paper:

Yuksel, A. K., & Ar, Y. (2023). A Machine Learning Approach to Malware Detection Using Application Programming Interface Calls (MDAPI). Traitement du Signal, 40(4).

@article{yuksel2023machine,
  title={A Machine Learning Approach to Malware Detection Using Application Programming Interface Calls (MDAPI).},
  author={Yuksel, Adnan Kutay and Ar, Yilmaz},
  journal={Traitement du Signal},
  volume={40},
  number={4},
  year={2023}
}

License

This repository is shared for educational purposes. Please refer to the original dataset terms for any usage restrictions.

Contact

For any questions regarding this repository, please contact Adnan Kutay Yüksel.