Polymorphic malware detection based on dynamic analysis and supervised machine learning / Nur Syuhada Selamat

• Main Author: Selamat, Nur Syuhada
• Format: Thesis
• Language: English
• Published: 2021
• Subjects: Electronic Computers. Computer Science
• Online Access: https://ir.uitm.edu.my/id/eprint/59811/1/59811.pdf; https://ir.uitm.edu.my/id/eprint/59811/

Currently, the size of malware grows faster each year and poses a thoughtful global security threat. The number of malware developed is increasing as computers became interconnected, at an alarming rate in the 1990s. This scenario caused a rising number of malware. It also caused many protections are developed to fight the malware. The most common method of detecting malware relies on signature-based detection. Unfortunately, this method is no longer effective to handle more advanced malware such as polymorphic malware that poses a thoughtful threat to the modern computing. Malware authors have created them to be more challenging to be evaded from antivirus scanner. Extracting the behaviour of polymorphic malware is one of the major issues that affect the detection result.The main idea in this work is focus the behaviour(dynamic) of polymorphic malware infect in computer system and to extract feature selection and evaluate a limited set of dataset in order to improve detection of polymorphic malware.This study used dynamic analysis and machine learning to improve malware detection.This research demonstrated improved polymorphic malware detection can be achieved with machine learning.This research used four types of machine algorithm which are K-Nearest Neighbours, Decision Tree, Logistic Regression, and Random Forest. As with most studies,careful attention was paid to false positive and false negative rates which reduce their overall detection accuracy and effectiveness.The result showed that the Random Forest algorithm is the best detection accuracy compares to others classifier with 99 % on a relatively small dataset. The benefit of this work indicated that the implementation of a feature selection technique plays an important role in machine learning algorithms to increase the performance of detection.