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{199663,
        author = {Manthan Sanap and Vitthal Kamble and Aditya Patil and Smith Shinde},
        title = {AI-BASED PHISHING DETECTION SYSTEM FOR DETECTING MALICIOUS WEBSITES AND EMAILS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {14934-14938},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199663},
        abstract = {Phishing attacks represent one of the most persistent and damaging forms of cybercrime, in which malicious actors impersonate legitimate institutions through fraudulent websites and deceptive email messages to steal sensitive user credentials and financial information. As digital communication continues to expand globally, the frequency and sophistication of these attacks have escalated considerably, overwhelming conventional detection mechanisms that rely on static databases and manually defined rules. This paper presents an Artificial Intelligence-based phishing detection system designed to identify malicious websites and phishing emails with greater accuracy and adaptability than traditional approaches. The proposed system integrates Machine Learning algorithms trained on a diverse feature set extracted from URL structure, domain registration characteristics, and email content metadata. By automating both the feature extraction and classification stages of the detection pipeline, the system can analyze incoming content in real time and produce reliable predictions regarding its legitimacy. Experimental analysis demonstrates that the AI-based approach achieves substantial gains in detection accuracy, precision, and recall compared to blacklist-based and rule-driven baselines, thereby providing organizations and individual users with an intelligent, scalable, and proactive layer of cybersecurity protection.},
        keywords = {Phishing Detection, Machine Learning, Malicious URL Analysis, Cybersecurity, Email Classification, Feature Extraction, Artificial Intelligence.},
        month = {April},
        }