Published in: Journal of Computer Science and Engineering in Innovations and Research (ISSN No: 3049-1762 online)
Publication Date: May 15, 2025
In today's digital world, phishing attacks have become a major cybersecurity threat, tricking users into revealing sensitive information like passwords and financial details. These attacks often mimic legitimate websites, making detection challenging. This project presents a Phishing URL Detector that utilizes machine learning to accurately classify URLs as legitimate or malicious.
By extracting key features such as URL length, special character usage, and suspicious domain extensions, the system establishes a strong analytical foundation. Advanced machine learning algorithms, including Random Forest and Support Vector Machines (SVM), are employed to train the model for high accuracy in phishing detection. Feature selection techniques ensure optimal performance and minimize false positives.
Beyond model accuracy, the project emphasizes scalability and real-world applicability. It addresses challenges in large-scale data processing and real-time classification, making it a practical solution for cybersecurity defenses. By integrating this system into security frameworks, organizations can proactively detect and block phishing attempts. This Phishing URL Detector plays a crucial role in mitigating online fraud and identity theft, protecting both individuals and businesses. By strengthening cybersecurity measures, it helps create a safer digital environment, reducing the risks associated with phishing attacks.
Phishing URL Detection, Cybersecurity, Machine Learning, URL Classification, Random Forest, Support Vector Machine