Malware Detection Using Machine Learning
Trung, Nguyen (2024)
2024
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2024052415250
https://urn.fi/URN:NBN:fi:amk-2024052415250
Tiivistelmä
In our increasingly digital world, the threat of malware is a growing concern for all internet users. Traditional methods of detecting malware are becoming less effective as cyber threats become more sophisticated, particularly in the case of polymorphic malware, which can change its identifiable features to avoid detection.
This thesis examines the use of machine learning in detecting malware, focusing specifically on three distinct algorithms: Decision Trees, Random Forests, and Support Vector Machines. These algorithms are trained using data extracted from Portable Executable (PE) files, which are commonly used formats for executables and object code.
This research introduces suggested approaches for malware classification and detection using machine learning, along with the principles for its execution. Furthermore, the conducted study can serve as a foundation for additional exploration in the field of malware examination utilizing machine learning techniques.
This thesis examines the use of machine learning in detecting malware, focusing specifically on three distinct algorithms: Decision Trees, Random Forests, and Support Vector Machines. These algorithms are trained using data extracted from Portable Executable (PE) files, which are commonly used formats for executables and object code.
This research introduces suggested approaches for malware classification and detection using machine learning, along with the principles for its execution. Furthermore, the conducted study can serve as a foundation for additional exploration in the field of malware examination utilizing machine learning techniques.