A Hybrid Temporal Graph Neural Network Framework with Automated Response for Digital Fraud Detection in Cloud Environments
DOI:
https://doi.org/10.63345/sjaibt.v3.i2.103Keywords:
Digital Fraud Detection, Temporal Graph Neural Networks, Cloud Security, Automated Response, Perplexed Bayes Classifier, Anomaly DetectionAbstract
Digital fraud has escalated significantly with the rapid digitization of financial services, posing substantial economic threats to users, merchants, and financial institutions [1]. Traditional rule-based and conventional machine learning approaches struggle to keep pace with the dynamic and increasingly sophisticated nature of fraudulent activities [2]. This research presents a novel Hybrid Temporal Graph Neural Network (HTGNN) framework with automated response capabilities for digital fraud detection in cloud-based financial platforms. The proposed framework integrates three key innovations: (1) a temporal graph construction mechanism that models transactions, users, devices, and payment instruments as dynamic heterogeneous graphs with time-stamped edges [3]; (2) a hybrid detection architecture combining perplexed Bayes classification for feature-level anomaly scoring with graph neural networks for structural pattern recognition, building upon established perplexed Bayes methodologies [4]; and (3) an automated response module inspired by the automated anomaly detection patent [5], which initiates predefined mitigation actions—alerting administrators, isolating compromised accounts, blocking suspicious transactions, and triggering adaptive security policies—upon detection. The framework was evaluated on the IEEE-CIS Fraud Detection dataset [6] and a synthetic cloud transaction dataset, achieving a ROC-AUC of 0.89, with 97.3% accuracy, 96.8% sensitivity, and 97.9% specificity. Comparative analysis demonstrates improvements of 8.2% over standalone GNN approaches and 5.6% over traditional machine learning baselines. The automated response module achieved an average mitigation time of 187ms, demonstrating its suitability for real-time cloud deployment. These findings establish the HTGNN framework with automated response as a robust, scalable solution for next-generation digital fraud prevention in cloud environments.
Downloads
References
[1] J. He, "Cloud computing load balancing mechanism taking into account load balancing ant colony optimization algorithm," Computational Intelligence and Neuroscience, vol. 2022, Art. ID 3120883, 10 pages, 2022. DOI: https://doi.org/10.1155/2022/3120883
[2] B. Bapat, "AI-powered fraud detection in digital financial platforms: A state-of-the-art survey," International Journal of Advanced Research in Computer Science, vol. 17, no. 3, p. 45, 2026. DOI: https://doi.org/10.26483/ijarcs.v17i3.7443
[3] D. Saldaña-Ulloa, G. De Ita Luna, and J. R. Marcial-Romero, "A temporal graph network algorithm for detecting fraudulent transactions on online payment platforms," Algorithms, vol. 17, no. 12, p. 552, 2024. DOI: https://doi.org/10.3390/a17120552
[4] N. Mishra, R. K. Singh, and S. K. Yadav, "Detection of DDoS vulnerability in cloud computing using the perplexed Bayes classifier," Computational Intelligence and Neuroscience, vol. 2022, Art. ID 9151847, 13 pages, 2022. DOI: https://doi.org/10.1155/2022/9151847
[5] H. K. Mistry, A. M. Goswami, and C. C. Mavani, "Automated anomaly detection and response system for enhancing cloud security," Indian Patent Application, Jul. 2024.
[6] IEEE, "IEEE-CIS Fraud Detection dataset," Kaggle Competition. [Online]. Available: https://www.kaggle.com/competitions/ieee-fraud-detection, 2024.
[7] F. S. Al-Anzi, S. K. Yadav, and J. Soni, "Cloud computing: Security model comprising governance, risk management and compliance," in Proc. 2014 Int. Conf. Data Mining and Intelligent Computing (ICDMIC), Sep. 2014. DOI: https://doi.org/10.1109/ICDMIC.2014.6954232
[8] D. Saldaña-Ulloa and G. De Ita Luna, "Detección de fraude digital mediante el uso de grafos," CIENCIA ergo-sum, vol. 33, 2025. DOI: https://doi.org/10.30878/ces.v33n0a49
[9] Seon, "Credit card fraud detection: The complete guide." [Online]. Available: https://seon.io/resources/credit-card-fraud-detection, 2024.
[10] C. Malone, "Online payment fraud: Market forecasts, emerging threats and segment analysis 2023–2028," Juniper Research, 2023.
[11] Stripe, "Fraudulent transactions 101: What causes them and how businesses can act." [Online]. Available: https://stripe.com/in/resources/more/fraudulent-transactions-101, 2024.
[12] G. Saporta and S. Maraney, Fraud Prevention Evaluation and Investment in Practical Fraud Prevention. Sebastopol, CA: O'Reilly Media, 2022.
[13] U. A. Butt, M. Mehmood, S. B. H. Shah et al., "A review of machine learning algorithms for cloud computing security," Electronics, vol. 9, no. 9, p. 1379, 2020. DOI: https://doi.org/10.3390/electronics9091379
[14] FATF-Interpol-Egmont Group, "Illicit financial flows from cyber-enabled fraud," FATF, Paris, 2023.
[15] "Graph neural networks for financial fraud detection: A review," Frontiers of Computer Science, vol. 19, no. 9, 2025. DOI: https://doi.org/10.1007/s11704-024-40474-y
[16] S. Rao et al., "Modelling graph dynamics in fraud detection with attention," arXiv:2006.10637, 2022.
[17] BBC, "Santander staff and '30 million' customers backed." [Online]. Available: https://www.bbc.com/news/articles/c6ppv06e-3n8o, 2024.
[18] Seon, "Bank account takeover attacks: How to keep safe." [Online]. Available: https://seon.io/resources/bank-account-takeover-attacks, 2024.
[19] R. Sulaiman, V. Schetinin, and P. Sant, "Review of machine learning approach on credit card fraud detection," Human-Centric Intelligent Systems, vol. 2, no. 1–2, pp. 55–68, 2022. DOI: https://doi.org/10.1007/s44230-022-00004-0
[20] R. V. Deshmukh and K. K. Devadkar, "Understanding DDoS attack & its effect in cloud environment," Procedia Computer Science, vol. 49, pp. 202–210, 2015. DOI: https://doi.org/10.1016/j.procs.2015.04.245
[21] L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. DOI: https://doi.org/10.1023/A:1010933404324
[22] K. Fu, D. Cheng, Y. Tu, and L. Zhang, "Credit card fraud detection using convolutional neural networks," Neural Information Processing, vol. 9949, pp. 483–490, 2016. DOI: https://doi.org/10.1007/978-3-319-46675-0_53
[23] S. Rana and M. J. C., "A survey on graph neural network approaches for fraud detection in blockchain networks," International Journal for Multidisciplinary Research, 2026.
[24] W. L. Hamilton, R. Ying, and J. Leskovec, "Inductive representation learning on large graphs," in Proc. 31st Int. Conf. Neural Information Processing Systems, pp. 1025–1035, Long Beach, CA, 2017.
[25] Z. Liu, C. Chen, X. Yang et al., "Heterogeneous graph neural networks for malicious account detection," arXiv:2002.12307, 2020.
[26] E. Rossi, B. Chamberlain, F. Frasca, D. Eynard, F. Monti, and M. Bronstein, "Temporal graph networks for deep learning on dynamic graphs," arXiv:2006.10637, 2020.
[27] H. Fan, Y. Jiao, M. Wang et al., "Fraud learns too: Continual graph learning under strategic adversarial drift in dynamic networks," Scientific Reports, 2026. DOI: https://doi.org/10.1038/s41598-026-60997-7
[28] B. Lebichot, F. Braun, O. Caelen, and M. Saerens, "A graph-based, semi-supervised, credit card fraud detection system," in Complex Networks & Their Applications V, pp. 721–733, 2017. DOI: https://doi.org/10.1007/978-3-319-50901-3_57
[29] S. Maes, K. Tuyls, B. Vanschoenwinkel, and B. Manderick, "Credit card fraud detection using Bayesian and neural networks," in Proc. 1st Int. NAISO Congr. Neuro Fuzzy Technol., Havana, Cuba, 2002.
[30] S. Rana and M. J. C., "A survey on graph neural network approaches for fraud detection in blockchain networks," International Journal for Multidisciplinary Research, 2026. DOI: https://doi.org/10.36948/ijfmr.2026.v08i03.77316
[31] S. K. Yadav, D. K. Tayal, S. N. Shivhare, and S. Naresh Shivhare, "Perplexed Bayes classifier-based secure and intelligent approach for aspect level sentiment analysis," International Journal of Advanced Intelligence Paradigms, vol. 13, no. 1/2, p. 15, 2019. DOI: https://doi.org/10.1504/IJAIP.2019.099941
[32] N. Mishra and R. K. Singh, "DDoS vulnerabilities analysis and mitigation model in cloud computing," Journal of Discrete Mathematical Sciences and Cryptography, vol. 23, no. 2, pp. 535–545, 2020. DOI: https://doi.org/10.1080/09720529.2020.1729503
[33] K. Dhingra and S. K. Yadav, "Spam analysis of big reviews dataset using fuzzy ranking evaluation algorithm and Hadoop," International Journal of Machine Learning and Cybernetics, vol. 10, no. 8, pp. 2143–2162, 2019. DOI: https://doi.org/10.1007/s13042-017-0768-3
[34] "Cloud resource risk scenario assessment and remediation," U.S. Patent 12,537,837 B2, 2026.
[35] "Techniques for control plane level containment," U.S. Patent 12,468,807, 2025.
[36] Y. Dou, Z. Liu, L. Sun, Y. Deng, H. Peng, and P. S. Yu, "Enhancing graph neural network-based fraud detectors against camouflaged fraudsters," arXiv, 2020. DOI: https://doi.org/10.1145/3340531.3411903
[37] C. Amine, S. Ben Alla, and A. Ezzati, "Makespan optimisation in cloudlet scheduling with improved DQN algorithm in cloud computing," Scientific Programming, vol. 2021, Art. ID 7216795, 11 pages, 2021. DOI: https://doi.org/10.1155/2021/7216795
[38] Ul Haq, J. P. Li, M. H. Memon, S. Nazir, and R. Sun, "A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms," Mobile Information Systems, vol. 2018, Art. ID 3860146, 21 pages, 2018. DOI: https://doi.org/10.1155/2018/3860146
[39] M. Idhammad, K. Afdel, and M. Belouch, "Detection system of HTTP DDoS attacks in a cloud environment based on information theoretic entropy and random forest," Security and Communication Networks, vol. 2018, Art. ID 1263123, 13 pages, 2018. DOI: https://doi.org/10.1155/2018/1263123
[40] X. Xiao et al., "Heterogeneous graph attention network," in Proc. ACM Conference, 2019.
[41] L. Dhanabal and S. P. Shantharajah, "A study on NSL-KDD dataset for intrusion detection system based on classification algorithms," International Journal of Advanced Research in Computer and Communication Engineering, vol. 4, no. 6, pp. 446–452, 2015.
[42] M. Fey and J. E. Lenssen, "Fast graph representation learning with PyTorch Geometric," arXiv:1903.02428, 2019.
[43] Paszke et al., "PyTorch: An imperative style, high-performance deep learning library," in Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035, 2019.
[44] F. Pedregosa et al., "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[45] W. McKinney, "Data structures for statistical computing in Python," in Proc. 9th Python in Science Conf., pp. 56–61, 2010. DOI: https://doi.org/10.25080/Majora-92bf1922-00a
[46] C. R. Harris et al., "Array programming with NumPy," Nature, vol. 585, pp. 357–362, 2020. DOI: https://doi.org/10.1038/s41586-020-2649-2
[47] C. S. Carlos, "Perplexed Bayes classifier," in Proc. 12th Int. Conf. Natural Language Processing, Trivandrum, India, Dec. 2015.
[48] Y. Jiang, B. Qiu, C. Xu, and C. Li, "The research of clinical decision support system based on three-layer knowledge base model," Journal of Healthcare Engineering, Art. ID 6535286, 8 pages, 2017. DOI: https://doi.org/10.1155/2017/6535286
[49] T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, pp. 785–794, 2016. DOI: https://doi.org/10.1145/2939672.2939785
[50] J. Shroff, R. Walambe, S. K. Singh, and K. Kotecha, "Enhanced security against volumetric DDoS attacks using adversarial machine learning," Wireless Communications and Mobile Computing, vol. 2022, Art. ID 5757164, 10 pages, 2022. DOI: https://doi.org/10.1155/2022/5757164
[51] X. Yu, W. Yu, S. Li, X. Yang, Y. Chen, and H. Lu, "Web DDoS attack detection method based on semisupervised learning," Security and Communication Networks, vol. 2021, Art. ID 9534016, 10 pages, 2021. DOI: https://doi.org/10.1155/2021/9534016
[52] N. O. Ogwara, K. Petrova, and M. L. Yang, "Towards the development of a cloud computing intrusion detection framework using an ensemble hybrid feature selection approach," Journal of Computer Networks and Communications, vol. 2022, Art. ID 5988567, 16 pages, 2022. DOI: https://doi.org/10.1155/2022/5988567
[53] M. Eshaty, H. Faris, and N. Obeid, "A competitive swarm optimizer with hybrid encoding for simultaneously optimizing the weights and structure of extreme learning machines for classification problems," International Journal of Machine Learning and Cybernetics, vol. 11, no. 8, pp. 1801–1823, 2020. DOI: https://doi.org/10.1007/s13042-020-01073-y
[54] Rangapur, T. Kanakam, and A. Jubbison, "DDoSDet: An approach to detect DDoS attacks using neural networks," arXiv:2201.09514, 2022.
[55] O. Cepheli, S. Buyukcora, and G. Karabulut Kurt, "Hybrid intrusion detection system for DDoS attacks," Journal of Electrical and Computer Engineering, pp. 1–8, 2016. DOI: https://doi.org/10.1155/2016/1075648
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Scientific Journal of Artificial Intelligence and Blockchain Technologies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The license allows re-users to share and adapt the work, as long as credit is given to the author and don't use it for commercial purposes.
