Spider bird swarm algorithm with deep belief network for malicious JavaScript detection

Abstract

JavaScript is employed in vast scenarios like web applications, NodeJS, and hybrid-mobile applications. Moreover, JavaScript is a core component in the social network because of its outstanding cross-platform. However, the flexibility of JavaScript made these applications more prone to attacks that induce malicious behaviors in the code. This paper proposes a hybrid optimization model, namely the Spider-based Bird swarm algorithm (S-BSA) algorithm for malicious JavaScript detection. The proposed S-BSA is designed by the integration of Spider Monkey Optimization (SMO) and Bird Swarm algorithm (BSA). The attributes like Boolean, execution time, function calls, break statements, and conditional statements are considered from the datasets. After the extraction of features, Box-Cox transformation is applied to normalize data. Moreover, a Deep belief network (DBN) is employed to classify normal and malicious JavaScript codes. The classification is progressed with DBN, wherein the training of DBN is performed with the proposed S-BSA. The proposed S-BSA algorithm outperformed other methods with maximal accuracy of 0.944, maximal TPR of 0.958, and minimal FPR of 0.081.