An Ensemble-Based Parallel Deep Learning Classifier With PSO-BP Optimization for Malware Detection

Abstract

Digital networks and systems are susceptible to malicious software (malware) attacks. Deep learning (DL) models have recently emerged as effective methods to classify and detect malware. However, DL models often relies on gradient descent optimization in learning, i.e., the Back-Propagation (BP) algorithm; therefore, their training and optimization procedures suffer from several limitations, such as high computational cost and local suboptimal solutions. On the other hand, ensemble methods overcome the shortcomings of individual models by consolidating their strengths to increase performance. In this paper, we propose an ensemble-based parallel DL classifier for malware detection. In particular, a stacked ensemble learning method is developed, which leverages five DL base models and a neural network as a meta model. The DL models are trained and optimized with a hybrid optimization method based on BP and Particle Swarm Optimization (PSO) algorithms. To improve scalability and efficiency of the ensemble method, a parallel computing framework is exploited. The proposed ensemble method is evaluated using five malware datasets (namely, Drebin, NTAM, TOP-PE, DikeDataset, and ML-Android), and high accuracy rates of 99.2%, 99.3%, 98.7%, 100%, and 100% have been achieved, respectively. Its parallel implementation also significantly enhances the computational speed by a factor up to 6.75 times. These results ascertain that the proposed ensemble method is effective, efficient, and scalable, outperforming many other compared methods in malware detection.