Malicious Urls Detection Using Convolutional Neural Networks and Deep

Abstract

The World Wide Web supports a good range of criminal activities like spam advertised e-commerce, financial fraud and malware dissemination. Nowadays Machine learning and Deep learning algorithms are a popular trend for the security aspects. Activity which requires the user to take some action, like clicking on a desired Uniform Resource Locator (URL) may result in some output This project aims to create a Web-App for the detection of malicious URLs based on characters as text classification features.Since the malicious keywords are unique to URLs, use of feature representation method of URLs based on malicious keywords will be used.