Web Phishing Detection using Machine Learning
N Kumaran1, Purandhar Sri Sai2, Lokesh Manikanta3
1N Kumaran, Assistant Professor, Department of Computer Science and Engineering, Sri Chandrasekharendra Saraswathi Viswa Mahavidyalaya, Kanchipuram (Tamil Nadu), India.
2Purandhar Sri Sai*, B.E Student, Department of Computer Science and Engineering, Sri Chandrasekharendra Saraswathi Viswa Mahavidyalaya, Kanchipuram (Tamil Nadu), India.
3Lokesh Manikanta, B.E Student, Department of Computer Science and Engineering, Sri Chandrasekharendra Saraswathi Viswa Mahavidyalaya, Kanchipuram (Tamil Nadu), India.
Manuscript received on February 28, 2022. | Revised Manuscript received on March 27, 2022. | Manuscript published on March 30, 2022. | PP: 56-59 | Volume-11, Issue-4, March 2022 | Retrieval Number: 100.1/ijitee.C98040311422 | DOI: 10.35940/ijitee.C9804.0311422
Open Access | Ethics and 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: A web service is one of the most important Internet communications software services. Using fraudulent methods to get personal information is becoming increasingly widespread these days. However, it makes our lives easier, it leads to numerous security vulnerabilities to the Internet’s private structure. Web phishing is just one of the many security risks that web services face. Phishing assaults are usually detected by experienced users however, security is a primary concern for system users who are unaware of such situations. Phishing is the act of portraying malicious web runners as genuine web runners to obtain sensitive information from the end-user. Phishing is currently regarded as one of the most dangerous threats to web security. Vicious Web sites significantly encourage Internet criminal activity and inhibit the growth of Web services. As a result, there has been a tremendous push to build a comprehensive solution to prevent users from accessing such websites. We suggest a literacy-based strategy to categorize Web sites into three categories: benign, spam, and malicious. Our technology merely examines the Uniform Resource Locator (URL) itself, not the content of Web pages. As a result, it removes run-time stillness and the risk of drug users being exposed to cyber surfer-based vulnerabilities. When compared to a blacklisting service, our approach performs better on generality and content since it uses learning techniques.
Keywords: Security; Web Services; URL; Vulnerabilities
Scope of the Article: Machine Learning