Enhanced Malware Detection in Windows Applications Using Ensemble Learning Techniques

Abstract

In order to protect computer systems from attacks that compromise their functionality and security, malware detection is crucial. To protect computer systems from attacks that compromise their functionality and security, malware detection is crucial. The goal of malware detection is to identify and remove malicious software that compromises the availability, confidentiality, or integrity of computer systems. Detecting malware in applications is a dynamic area of cybersecurity. Efficiency and accuracy are essential. The purpose of this study is to use machine learning techniques to enhance applications' capacity to detect malware. This work will examine malware detection and classification components using Adaboost, a modern machine learning (ml) technique. The proposed study makes use of the "Windows Malware Detection Dataset," which is a publicly available dataset. In order to select the best features, We employed an ensemble learning strategy. Our objective is to develop a dependable detection system that integrates state-of-the-art machine learning techniques. This project develops learning strategies using machine learning algorithms, including supervised and unsupervised learning techniques. The suggested modelbuilds a classification and recognition model using machine learning algorithms, including supervised and unsupervised learning techniques. The suggested methodology includes data preparation, model training, and evaluation in order to produce a dependable detection system. With a 99.9% accuracy rate, the suggested methodology performs better than current models.