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{199108,
        author = {Mahammad Umar and k Ganesh and K sravan and Kaveti Penchalaiah and MADDIREDDY HARSHA VARDHAN REDDY},
        title = {Design and implementation of GNN based fraud detection system for cryptocurrency},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12574-12579},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199108},
        abstract = {The rapid evolution of cryptocurrency systems has introduced significant challenges in ensuring financial security, particularly in detecting fraudulent activities. Due to the decentralized nature of blockchain technology and the anonymity of users, identifying fraudulent transactions has become increasingly complex. Traditional fraud detection methods, which rely on rule-based systems or simple machine learning models, are not capable of capturing the intricate relationships between transactions and users. This project presents a Graph Neural Network (GNN) based approach to detect fraudulent activities in cryptocurrency networks. The core idea is to model blockchain transaction data as a graph, where nodes represent user accounts and edges represent transactions between them. By leveraging advanced models such as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT), the system is able to learn both structural and relational patterns within the network. The proposed system demonstrates improved performance in terms of accuracy, precision, and recall when compared to traditional approaches. It effectively identifies complex fraud patterns such as money laundering and multi-step transactions. This research highlights the importance of graph-based learning techniques in addressing modern cybersecurity challenges and provides a scalable solution for fraud detection in decentralized financial systems.},
        keywords = {Cryptocurrency, Blockchain, Fraud Detection, Graph Neural Networks, GCN, GAT, Machine Learn},
        month = {April},
        }