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{200959,
        author = {Om Wath and Dr. Kishor Tayade and Om Raut and Tushar Rathod and Om Gulhane},
        title = {FraudShield AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {3172-3176},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200959},
        abstract = {This paper presents FraudShield AI, an AI-powered multi-modal cyber threat detection system designed to identify phishing URLs, spam messages, fraudulent emails, and malicious APK files in real time. The system uses a hybrid approach combining a Multinomial Naive Bayes classifier with TF-IDF bigram features and a heuristic rule engine. The heuristic module detects brand mimicry, suspicious domains, phishing keywords, and urgency patterns. Implemented as a Flask web application, the system achieves 92.1% accuracy and outperforms standalone machine learning models.},
        keywords = {FraudShield AI, cyber threat detection, phishing detection, spam filtering, APK analysis, Naive Bayes, TF-IDF, heuristic analysis.},
        month = {May},
        }