Authors : D R Dinesh Kumar; S. Sujeeth Reddy; B. Aditya; T. Neetha

Volume/Issue : Volume 9 - 2024, Issue 5 - May

Google Scholar : https://tinyurl.com/fjdxz8kb

Scribd : https://tinyurl.com/y68whffm

DOI : https://doi.org/10.38124/ijisrt/IJISRT24MAY1622

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The proliferation of phishing attacks represents a critical challenge to cybersecurity, necessitating the development of advanced detection systems. Our project, "Phishing Website Detection Using Machine Learning," aims to address this challenge by leveraging sophisticated machine learning algorithms to meticulously analyze and distinguish phishing websites from legitimate ones. By systematically examining various features and patterns within web content, such as URL anomalies, use of secure protocols, and other distinctive markers, the project seeks to accurately identify and classify phishing attempts. The approach encompasses comprehensive data collection, meticulous preprocessing to enhance data quality, and the employment of diverse machine learning models tailored for optimal performance in real-time detection scenarios. This endeavor not only focuses on enhancing online security measures but also on ensuring user-friendly interaction to facilitate widespread adoption. Through the integration of advanced machine learning techniques and a keen focus on the dynamic nature of cyber threats, this project endeavors to contribute significantly to the proactive defense against phishing attacks, thereby bolstering the integrity and trustworthiness of online spaces. A pivotal aspect of our methodology is the adoption of gradient boosting algorithms, a powerful ensemble learning technique renowned for its effectiveness in handling complex and nonlinear data. By integrating gradient boosting into our analysis, we significantly improve the model's ability to learn from and adapt to the intricacies of phishing website characteristics, ensuring a robust detection mechanism. This advanced algorithm iteratively corrects errors from previous models and combines weak predictors to form a strong predictive model, offering unparalleled accuracy in real-time phishing detection. The choice of gradient boosting reflects our commitment to employing cutting-edge technology to tackle the dynamic and evolving nature of cyber threats, balancing detection sensitivity with minimal false positives to ensure a seamless web experience for users.

References :

1. 6th International Conference on Trends in Electronics and Informatics (ICOEI) | 978-1-6654-8328-5/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICOEI53556.2022.9777221 2022
2. 2nd International Conference on Advanced Research in Computing (ICARC) | 978-1-6654-0741-0/22/$31.00 ©2022 IEEE| DOI: 10.1109/ICARC54489.2022.9753802 2022
3. International Conference on Information Networking (ICOIN) | 978-1-6654-1332-9/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICOIN53446.2022.9687204 2022
4. IEEE India Council International Subsections Conference (INDISCON) | 978-1-6654-6601-1/22/$31.00 ©2022 IEEE | DOI: 10.1109/INDISCON54605.2022.9862909 2022