Paper Key : IRJ************719
Author: D Lokesh,Adeppa Tharun Kumar,Abburi Karthik,G Karthikeya Bhargava Sharma,Dr.r.karunia Krishnapriya,Mr.n.vijaya Kumar,Mr.pandreti Praveen,Mr.v Shaik Mohammad Shahil
Date Published: 02 Apr 2025
Abstract
Phishing is a common cyberthreat that uses phony websites to trick people into disclosing private information. This study introduces a phishing detection system that analyzes URLs and categorizes them as malicious or authentic using a hybrid machine learning technique. In addition to content-based and behavioral indications, the system extracts important URL-based parameters like length, domain age, presence of special characters, and entropy. To improve detection accuracy, a variety of supervised machine learning methods are used, including random forest, SVM, and neural networks. Prior to engaging with them, suggest high precision and recall. When compared to conventional blacklist-based techniques, the approach greatly improves phishing detection and raises awareness of cybersecurity Keywords: Phishing Detection, Cybersecurity, Machine Learning, Hybrid Model, URL Analysis, Feature Extraction, Supervised Learning, Web Security, Random Forest, Neural Networks, Cyber Threats
DOI Requested