Advances in Cyber Security Analytics and Decision Systems

Abstract

Phishing is a critical issue that faces the digital security. The straightforwardness of the web and Internet uncovered open doors for offenders to transfer malevolent substance at the same time with the upgrade of online business trades, for example, phishing – the demonstration of taking individual data which ascends in number. Internet clients’ costs have been increased to billions of dollars for each year due to phishing. Phishers use parodied email, Uniform Resource Locator (URL) locations of phony sites, and phishing programming to take individual data and monetary record subtleties, for example, usernames and passwords. The boycott system is definitely not a sufficient method to remain safe from the cybercriminals. Hence, phishing site pointers must be considered for this reason, with the presence and utilization of machine learning calculations. The current techniques make utilization of all separated attributes in the phishing URL location, prompting high false positive rate. In this manner, the proposed work manages strategies for distinguishing phishing web destinations by investigating different attributes of genuine and phishing URLs utilizing profound learning procedures, for example, deep Boltzmann machine (DBM), stacked auto-encoder (SAE), and deep neural network (DNN). DBM and SAE are utilized for pre-preparing the model with a superior portrayal of data for attribute determination, among which SAE has accomplished lower misclassification mistake with nine and includes a diminished list of attributes and DNN is utilized for twofold grouping in distinguishing obscure URL as either a phishing URL or a genuine URL. The proposed framework accomplishes higher location rate of 94% with low false positive rate than other machine learning strategies.