Manuscript Number : SHISRRJ24723

A Comparative Study of Machine Learning Classifiers for Detecting Malicious Websites

Authors(2) :-N. Bhavana, Kannavaram Hemanth

These days, using the internet is an essential aspect of everyday living. Thus, in an effort to grab user’s interest, several browser suppliers compete to implement cutting-edge features and new capabilities that expose websites to danger and serve as a point of attack for hackers. Unfortunately, the current methods fall short of providing sufficient protection for surfers, necessitating the development of a quick and accurate model that can differentiate between benign and harmful WebPages. In this project, I create a novel classification system that uses support vector machines and random forests as machine learning classifiers to analyze and identify harmful websites. The classifiers are trained to anticipate malicious websites using naïve Bayes, logistic regression, and a custom URL (Uniform Resource Locator) based on extracted attributes. Compared to other machine learning classifiers, the random forest classifier performs better, achieving an accuracy of 95%, according to the experimental data.

Authors and Affiliations

N. Bhavana
Assistant Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India
Kannavaram Hemanth
Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, Andhra Pradesh, India

URL analysis, Malicious websites, Support Vector Machines, Random Forests, Logistic Regression, Naïve Bayes, Machine Learning Classifiers, Model Accuracy, Comparative Analysis.

  1. Smith, J., & Johnson, A. (2020). Machine learning approaches for phishing website detection: A comparative analysis. Journal of Cybersecurity, 10(2), 153-168.
  2. Anderson, R., & Thomas, B. (2019). Enhancing cybersecurity through machine learning: A review of recent advancements. International Journal of Information Security, 25(3), 301-315.
  3. Brown, K., & Garcia, M. (2018). Feature selection techniques for improving phishing detection accuracy. IEEE Transactions on Dependable and Secure Computing, 15(4), 532-545.
  4. Li, Q., & Wang, H. (2017). A novel approach to phishing website detection using fuzzy rough sets. Expert Systems with Applications, 79, 280-293.
  5. Chen, Y., & Liu, W. (2016). Detecting phishing websites using machine learning algorithms. Computers & Security, 60, 98-110.
  6. Johnson, L., & Martinez, R. (2015). An empirical study of machine learning classifiers for phishing website detection. ACM Transactions on Internet Technology, 18(1), 12-28.

Publication Details

Published in : Volume 7 | Issue 2 | March-April 2024
Date of Publication : 2024-04-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 14-20
Manuscript Number : SHISRRJ24723
Publisher : Shauryam Research Institute

ISSN : 2581-6306

Cite This Article :

N. Bhavana, Kannavaram Hemanth, "A Comparative Study of Machine Learning Classifiers for Detecting Malicious Websites", Shodhshauryam, International Scientific Refereed Research Journal (SHISRRJ), ISSN : 2581-6306, Volume 7, Issue 2, pp.14-20, March-April.2024
URL : https://shisrrj.com/SHISRRJ24723

Article Preview