GuardNet: An Ensemble-Based Malware Detection Model Using Machine Learning

Malware poses a significant threat to cybersecurity, with increasing complexity and sophistication in attacks. Traditional methods that rely on known malware signatures often struggle to keep up with the fast changes in malware, leading to increased risks of data breaches, financial losses, and privacy issues. This research aims to address this problem by creating an advanced ensemble-based malware detection model, GuardNet, that leverages advanced machine learning techniques to improve detection accuracy and efficiency. The proposed model utilizes several classifiers, including Support Vector Machine (SVM), Random Forest, XGBoost, and Multi-Layer Perceptron (MLP), and employs hyperparameter tuning for performance optimization. GuardNet uses two large, distinct, and publicly available datasets, each providing a unique set of malware samples, and demonstrates that the ensemble model outperforms individual classifiers, achieving an accuracy of $100 \%$ and an AUC of 1.00. This research highlights the importance of ensemble techniques in enhancing malware detection and offers practical implications for real-world applications.