DEVELOPMENT OF MALWARE CLASSIFICATION TECHNIQUE BASED ON MACHINE LEARNING NEURAL NETWORK AND DISCRETE-TIME MARKOV CHAIN

• Main Author: Claudia Lumban Gaol, Devani
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/66813
• Institution: Institut Teknologi Bandung

ABSTRACT DEVELOPMENT OF MALWARE CLASSIFICATION TECHNIQUE BASED ON MACHINE LEARNING NEURAL NETWORK AND DISCRETE-TIME MARKOV CHAIN By Devani Claudia Lumban Gaol NIM: 23219349 (Master’s Program in Electrical Engineering) Malware or Malicious Software is a computer program or software created and designed to interfere with,and damage a computer system, which is part of a cybercrime activity. Malware detection techniques are categorized into static methods and dynamic methods. Both of these techniques still have weaknesses, so machine learning is used to overcome the weaknesses of the two techniques. Convolutional Neural Network (CNN) is one of neural network’s type that usually used to detect and classify malware in image data. However, in some classification tests with certain datasets, CNN still cannot work optimally. Therefore, a model development needed to improve the CNN’s performance in doing classification. This thesis proposes a malware classification method using CNN with feature extraction from the Discrete-Time Markov Chain transition probability model as input for knowledge transfer. The purpose of developing this algorithm is to provide better classification results compared to conventional CNN methods. Various scenarios were carried out to get the best performance comparison results. The best performance was obtained when the model was run with the Markov transition probability order 1 dataset with 94% accuracy, 95% precision, 95% recall, and 95% f1-score. Keywords: Malware, CNN, classification, Markov transition probability.