Malware Detection Using The Machine Learning Based Modified Partial Swarm Optimization Approach

Abstract

Malware analysis includes a crucial step after malware detection called malware categorization, which classifies dangerous files. There have been many reported static and dynamic methods for classifying malware up to this point. The ML-MD strategy presented in this study uses static methods to categorise various malware families and is based on machine learning. In order to detect malware, we create a new machine learning-based framework. The characteristics from the dataset are extracted in this case using principal component analysis (PCA). In order to offer the best malware detection solutions, introduce a machine learning-based Modified Particle Swarm Optimization (MPSO) algorithm. Improved Accuracy and detection rate using ML-based MPSO technique. The effectiveness of the suggested technique in detecting malware is demonstrated by the experimental results on several benchmark data sets, which greatly outperform alternative approaches.