Malware detection is an important factor in the security of the computer systems. However, currently utilized signature-based methods cannot provide accurate detection of attacks and polymorphic viruses. That is why the need for malware detection using machine learning arises. This work was motivated by the limitation of [1] in ‘Malware Detection Module using Machine Learning Algorithms to Assist in Centralized Security in Enterprise Networks’ that focuses on just the detection and classification neglecting home users because it’s processor heavy. The objective of this research is to design a security framework for malware detection using machine learning and also implement it. Feature selection (Filter method) was used to reduce 100,000 columns and 35 rows of features to 20 features, then three classifier algorithms were employed which are K-Nearest Neighbor, Decision Tree and Random Forest. The classifiers are trained and tested using the dataset(malware.csv) gotten from Malware Detection Kaggle. The results of the algorithms (KNearest Neighbor, Decision Tree and Random Forest) are respectively 96.53%,97.79% and 99.90%. The results were also compared with other researchers (Maqsood 2020and Sarang et al. 2013) work that used the same three classifiers, the results of Maqsood 2020 for Random Forest, Decision tree and K nearest neighbor are respectively 96.39%, 100%(overfit) and 99.4%, while the results of Sarang et al 2013 for Random Forest, Decision tree and K nearest neighbor are respectively 99.57%, 99.23%, and 99.06%.

Authors: Olaniyi Abiodun Ayeni, Otasowie Owolafe, Olabiyi Akinsola

Published in: International Conference for Internet Technology and Secured Transactions (ICITST-2021)

• Date of Conference: 7-9 December 2021
• DOI: 10.20533/ICITST.2021.0008
• ISBN: 978-1-913572-39-6
• Conference Location: Virtual (London, UK)