Development of Malware Detection Using Machine Learning

Adedayo-Ajayi, V. O.,  Ogundokun, R. O., Akande, H. B., Babatunde, A. N., Dubem, D. & Tunbosun, A. E.

Development of Malware Detection Using Machine Learning

Files

39 Development_of_Malware_Detection_Using_Machine_Learning.pdf(3.7 MB)

Date

2024-10-18

Authors

Adedayo-Ajayi, V. O., Ogundokun, R. O., Akande, H. B., Babatunde, A. N., Dubem, D. & Tunbosun, A. E.

Publisher

2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG)

Abstract

Abstract— With the continuous rise in computer tech, programmers and hacking occurrences are expanding and require additional security requests. Malware has been an extraordinary torment for computer clients around the world. Big organizations have gone into gigantic misfortunes due to an escape clause in security. In the current world of technology, Machine learning is considered a long-standing time and the foremost capable concept in innovation. The point is to utilize the machine learning concept and construct a show using gathering calculations that can be prepared effectively to identify malware in a framework. This extension is around the comparative consideration of standard machine learning and crossbreed calculations to determine how much effect a crossbreed machine learning calculation can have in distinguishing malware from traditional machine learning algorithms. In this study, we employ different machine-learning algorithms to detect malware. Our results show that Random Forest outperformed other machine learning algorithms with accuracy and average precision of 98% and 92%, respectively. These outcomes are crucial as malware becomes more prevalent and advanced. Keywords— Malware detection, Machine Learning, Random Forest.