Domain Detector - An Efficient Approach Of Machine Learning For Detecting Malicious Websites
DOI:
https://doi.org/10.63278/mme.vi.1663Keywords:
Phishing, URL detection, Machine Learning, Gradient Boosting Classifier, Cyber Security.Abstract
Phishers employ social engineering and mimic sites to trick users and organizations into divulging personal details such as account IDs, usernames, and passwords. Phishing URL detection, hence, in the face of this is of paramount significance. Machine learning and deep learning algorithms have been created to identify phishing URLs automatically. We use a Gradient Boosting Classifier which has been trained on a wide range of features and an extremely large corpus of data in our process. This enables the system to learn in real-time, reacting to new threats by incorporating recently detected phishing techniques, actual domain changes, and notes by experienced analysts. Our system analyzes the content of sites for harmful patterns and adds reputation-based features like domain age to aid in detection. With such sophisticated means, our system is highly resistant to phishing attacks preventing loss of funds and safeguarding confidential information.
Downloads
How to Cite
Issue
Section
License
Copyright (c) 2025 Mrs. T. Sai Priyanka, Kotari Sridevi, A. Sruthi, S. Laxmi Prasanna, B. Sahithi, P. Jyothsna

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their published articles online (e.g., in institutional repositories or on their website, social networks like ResearchGate or Academia), as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Except where otherwise noted, the content on this site is licensed under a Creative Commons Attribution 4.0 International License.