An Approach for Malicious JavaScript Detection Using Adaptive Taylor Harris Hawks Optimization-Based Deep Convolutional Neural Network

JavaScript has to become a pervasive web technology that facilitates interactive and dynamic Web sites. The extensive usage and the properties permit the authors to simply obfuscate the code and make JavaScript an interesting place for hackers. JavaScript is usually used for adding functionalities and improving the usage of web applications. Despite several merits and usages of JavaScript, the major issue is that several recent cyber-attacks like drive-by-download attacks utilized the susceptibility of JavaScript codes. This paper devises a novel technique for detecting malicious JavaScript. Here, JavaScript codes are fed to the feature extraction phase for extracting the noteworthy features that include execution time, function calls, conditional statements, break statements, and Boolean. The extracted features are further subjected to data transformation wherein log transformation is adapted to normalize the data. Then, feature selection is performed using mutual information.