Malware Detection using Machine Learning

Abstract

As the level of malware and viruses is on the rise, the prominence of effective detection systems is crucial. Malwares are the modern-day threats that have troubled major companies worldwide. This article explores in depth two powerful machine learning tools, Random Forest, Support Vector Machines in particular, for the detection of malware. Our study revealed the Random Forest's capacity to reach the upper detection accuracy limit of 98% by applying an analysis of a dataset of variousmalware samples. The feature selection process as well as the model improvement that we've adopted have substantially improved use of our approach for malware detection, and this is thereby highly crucial for organizations to fight against evolving cyber threats. The results of the present research support the ongoing actionsof strengthening cybersecurity security, therefore, providing invaluable information for proactive defense approach mechanisms against malicious software attacks.