Alfaruqi, Dhafin (2025) Perbandingan Metode Algoritma Machine Learning Support Vector Machine, NaÏve Bayes, Dan Logistic Regression Untuk Klasifikasi Malware Pada Pe Files. Other thesis, Universitas Islam Riau.

Text 203510490.pdf - Submitted Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

The rapid advancement of technology has led to an increase in malware threats to cybersecurity, particularly targeting Portable Executable (PE) files, which are often the focus of attacks. Traditional malware detection approaches are not always effective in addressing new malware variants. Therefore, the application of machine learning algorithms has become essential to enhance detection capabilities. This study aims to compare the performance of three machine learning algorithms: Support Vector Machine (SVM), Naïve Bayes, and Logistic Regression in classifying malware in PE files. The dataset used contains information about the PE file headers and labels indicating whether the data is malware or benign. The research methodology includes data collection, preprocessing, categorical feature encoding, data normalization, data splitting, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the SVM model performs the best with the highest accuracy, followed by Logistic Regression and Naïve Bayes. This study aims to provide insights into the strengths and weaknesses of each algorithm and contribute to further development in cybersecurity, particularly in malware detection based on PE files.

Actions (login required)

View Item