Phishing Website Detection with Analytics and Classification Using Machine Learning
- Version
- Download 6
- File Size 370.16 KB
- File Count 1
- Create Date 23 January 2026
- Last Updated 23 January 2026
Phishing Website Detection with Analytics and Classification Using Machine Learning
V. MAGESWARI., MCA
(Assistant Professor, Master of Computer Applications)
S. DHIVAGAR., MCA
Christ College of Engineering and Technology
Moolakulam, Oulgaret Municipality, Puducherry – 605010.
Abstract
The rapid expansion of online platforms and digital services has led to increasing security threats in the form of phishing websites that impersonate legitimate platforms to steal confidential user information [1], [2]. Traditional blacklist-based mechanisms are insufficient against newly created phishing websites due to their short lifespan and constantly evolving patterns [3], [4]. This paper proposes an integrated Phishing Website Detection System that analyzes website URLs, extracts phishing-related lexical and domain features, and classifies them as phishing or legitimate using supervised machine learning techniques [5], [6]. The system evaluates multiple classifiers including Random Forest, Decision Tree, Support Vector Classification, AdaBoost, and XGBoost using a benchmark phishing dataset [7], [8]. Experimental results demonstrate that XGBoost achieves the highest accuracy, outperforming other models by effectively capturing non-linear feature relationships [9], [10]. The system is deployed as a web platform using Flask, enabling users to submit URLs and receive real-time classification results along with analytics such as confidence scores, feature distribution graphs, and model performance comparisons [11]. The platform enhances usability and interpretability through visual analytics and supports scalable deployment for real-world cybersecurity applications [12]. The results highlight the importance of machine learning in combating modern phishing attacks and improving online safety [13], [14].
Keywords
Phishing detection, machine learning, XGBoost, Random Forest, URL feature extraction, Flask web application, cybersecurity, analytics.
Download