Survey on Detection of Malicious Web Pages and URLs using Machine Learning
Samkeet Shah1, Dakshil Shah2, Lakshmi Kurup3
1Dakshil Shah, Department of Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai (Maharashtra), India.
2Samkeet Shah, Department of Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai (Maharashtra), India.
3Prof. Lakshmi Kurup, Department of Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai (Maharashtra), India.
Manuscript received on 13 October 2015 | Revised Manuscript received on 22 October 2015 | Manuscript Published on 30 October 2015 | PP: 32-35 | Volume-5 Issue-5, October 2015 | Retrieval Number: E2210105515/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Web based security threat is rising every day. Web pages serve as one of the primary ways for interaction with and for the users. However, certain web application or websites are directed to mislead the user and try to gain access to the user’s system in order to steal sensitive personal information. The old legacy based approaches on malicious web pages or URLs detection consist of using blacklist that check the URL against an existing database of flagged and suspicious links. The World Wide Web has progressed significantly, with the active use of JavaScript, ActiveX, Flash Player and related technologies. The heavy use of these technologies has improved the user experience and available services on web pages. Attackers tend to find security loopholes into these technologies and use them to their advantage. This method however fails to detect ever evolving attack methods. Thus there is a need to use methods that can adopt to and evolve simultaneously with the advancing threats. Hence, in this paper we have reviewed various types of web based attacks and machine learning techniques to detect malicious web pages and URLs.
Keywords: Machine Learning, Malicious Webpages, Web Security
Scope of the Article: Machine Learning