Optimizing Malware Detection Using Back Propagation Neural Network and Hyperparameter Tuning

Abstract

The escalating growth of the internet has led to an increase in cyber threats, particularly malware, posing significant risks to computer systems and networks. This research addresses the challenge of developing sophisticated malware detection systems by optimizing the Back Propagation Neural Network (BPNN) with hyperparameter tuning. The specific focus is on fine-tuning essential hyperparameters, including dropout rate, number of neurons in hidden layers, and number of hidden layers, to enhance the accuracy of malware detection. A Back Propagation Neural Network (BPNN) with dropout regularization is trained on an extensive dataset as part of the research design. Hyperparameter optimization is conducted using GridSearchCV, with experiments varying learning rates and epochs. The best configuration achieves outstanding results, with 98% accuracy, precision, recall, and F1-score. The proposed approach presents an efficient and reliable solution to bolster cybersecurity systems against malware threats.