Malware detection by using two-layer stacking SVM classifier

Raja Mohd Anuar, Raja Nurul Aini (2021) Malware detection by using two-layer stacking SVM classifier. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

	Text (24 Pages) Malware detection by using two-layer stacking SVM classifier.pdf - Submitted Version Download (333kB)
	Text (Full Text) Malware detection by using two-layer stacking SVM classifier.pdf - Submitted Version Restricted to Repository staff only Download (1MB)

Abstract

Mobile device usage increased with new high technology that attracted the attacker to launch the attack, such as mobile malware. Mobile malware is malicious that is loaded into the device system and causes damage. Malware has become more prevalent in recent years. Nowadays, there are many techniques available to detect this attack. In this research, N-gram with opcode sequence dataset was used, focusing on mobile malware detection model. The dataset undergoes feature selection which is Information Gain and Chi-square, to reduce irrelevant data and redundant data. Then, the classifier used in this project is Support Vector Machine (SVM) to develop a model. The developed model will test and verify the accuracy with the test set. The project is giving hope to produce a system that can detect mobile malware attacks.

Actions (login required)

View Item