Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195141,
        author = {Krithika Kumar and B. Manisha Rani and Hamsa Gowlikar and Anusha Kommarajula},
        title = {Phishing Website Detection Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6474-6481},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195141},
        abstract = {Phishing attacks represent a major danger for international cybersecurity efforts. Hackers have developed better social engineering methods which they use to trick people into sharing their confidential financial details through fake websites. The existing detection methods which include rule-based systems and manual blacklisting fail to identify new zero-day attacks and emerging URL threats. This research presents an innovative detection system which uses machine learning to analyze URLs in real time based on their structural characteristics. The project collects multiple numerical features for training purposes which will be used to develop five classification algorithms including Logistic Regression Random Forest Decision Tree K-Nearest Neighbours and Linear Support Vector Machine. The data set provides character ratios and entropy measurements and URL length information from more than 566000 unique URLs. The results show high effectiveness across multiple performance indicators, including F1-score and accuracy and precision and recall. The K-Nearest Neighbours (KNN) algorithm achieved an accuracy of 96.39% while it produced an F1 score of 0.9137 which made it superior to all other algorithms. The most precise model operates through a browser extension which notifies users about dangerous websites. The demonstration shows practical applications of the system. The research demonstrates that automated threat detection through machine learning protection systems provides better security for users in digital environments.},
        keywords = {Classification Algorithms, Machine Learning, Phishing Website Detection, Cybersecurity, K-Nearest Neighbours, URL Feature Analysis.},
        month = {March},
        }