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{183777,
        author = {Veena H R and Dr. Sandeep},
        title = {Multi-Class Website Phishing Detection and Risk Assessment Using RNN-LSTM with SSL Certificate Validation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {2980-2987},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183777},
        abstract = {Phishing and related web-based attacks have become one of the most persistent threats to online security, targeting individuals and organizations through deceptive websites. Traditional detection systems often classify URLs into only two categories—phishing or legitimate—without distinguishing the type of attack or assessing the severity of risk. This limited perspective can reduce the usefulness of such systems in real-world decision-making. In this research, we propose a deep learning-based framework that employs Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models to analyze website URLs as sequential data and classify them into four attack categories: phishing, social engineering, spoofing, and business email compromise (BEC). To strengthen detection, the system integrates SSL/TLS certificate analysis, verifying the vendor and extracting metadata to enhance authenticity checks. Beyond classification, the framework evaluates each suspicious link by providing the potential attack level, depth of deception, and overall risk score. This combination of sequential learning and certificate-based validation allows the system to not only detect threats accurately but also explain the nature and severity of the attack. The proposed approach aims to support users, organizations, and security analysts with actionable intelligence, improving their ability to mitigate evolving phishing techniques effectively.},
        keywords = {Website Phishing Detection, RNN-LSTM, Multi-Class Classification, SSL Certificate Validation, Risk Assessment, Cybersecurity.},
        month = {August},
        }