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{184568,
        author = {Dr.Sunith GP and Ankitha sabhoji and santhosh SG},
        title = {Blockchain-Aided Spoofed URLs Detection: A GNN and Rule-Based Fusion},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {2018-2023},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184568},
        abstract = {Phishing attacks have been a major threat in cybersecurity, plays with human trust by deceiving users to interact with fraudulent websites and imposes on technical vulnerabilities. Traditional detecting systems, such as signature-based rule- based methods, This often fail to identify original and obfuscated phishing URLs. This paper presents an intelligent and secure phishing detection system which combines the capabilities of Graph Neural Networks (GNNs) and rule-based feature analysis, integrated with the blockchain technology for fixed logging. The GNN model analyses the structural relationships within the URL using a graph-based representation, on the other hand the rule-based module examines key heuristic indicators which includes the presence of IP addresses, URL length, and HTTPs usage. Each prediction of GNN is logged into a private blockchain using a proof-of-work consensus to ensure transparency, traceability and for tamper-resistant. Additionally, disagreement cases between models are highlighted with rule- based explanations and blockchain traceability.},
        keywords = {Phishing Detection, GNN, Rule-Based Model, Blockchain, URL Classification, Cybersecurity},
        month = {December},
        }