Signal-Aware Fraud Detection: A Taxonomy for Sustainable and Lifecycle-Oriented Detection Architectures

• Sara Santedicola Ribeiro UnB
• Fabio Lucio Lopes de Mendonça UnB
• Laerte Peotta UnB

DOI: https://doi.org/10.5753/semish.2026.23979

Resumo

Online financial fraud is growing in scale, coordination and operational complexity, challenging detection systems to balance accuracy, interpretability, scalability and computational efficiency. This work proposes a signal-aware perspective for fraud detection centered on the observable evidence generated throughout fraudulent activity. Fraud-relevant signals are organized into temporal, distributional, structural and contextual families, which may be operationalized explicitly, implicitly or through hybrid representations. To contextualize signal emergence, the paper introduces a conceptual fraud lifecycle model that distinguishes strategic and operational reconnaissance activities and highlights the asymmetric observability of fraud across lifecycle stages. Building on this perspective, the paper analyzes how different detection paradigms operationalize signal families and examines the associated trade-offs involving computational complexity, latency, scalability and interpretability. By reframing fraud detection as a process-aware and systems-oriented problem grounded in signal emergence and operationalization, this work contributes towards the design of more explainable, efficient and operationally robust fraud detection systems.

Referências

ACFE (2026). Antifraud technology benchmarking report. Technical report, ACFE.

Akoglu, L., Tong, H., and Koutra, D. (2015). Graph-based anomaly detection and description: a survey. Data Mining and Knowledge Discovery.

Ares-Robledo, F.; Rifà-Pous, H. C. R. (2026). Graph neural networks for anomaly detection: a systematic review of dynamic temporal approaches. Artificial Intelligence Review, 59(129).

Bhattacharyya, S., Jha, S., Tharakunnel, K., and Westland, J. C. (2011). Data mining for credit card fraud: A comparative study. Decision Support Systems, 50(3):602–613. On quantitative methods for detection of financial fraud.

Castaño, J., Bustillo, J., Franch, X., and Martínez-Fernández, S. (2026). Data-driven multi-objective optimization of ml inference hardware configurations for energy, performance and cost. Sustainable Computing: Informatics and Systems, 50:101347.

Chen, Y., Zhao, C., Xu, Y., Nie, C., and Zhang, Y. (2025). Deep learning in financial fraud detection: Innovations, challenges, and applications. Data Science and Management.

Dal Pozzolo, A., Caelen, O., Johnson, R., and Bontempi, G. (2015). Calibrating probability with undersampling for unbalanced classification.

FBI (2026). Internet crime report 2025. Technical report, Internet Crime Complaint Center - IC3.

FEBRABAN (2025). Pesquisa febraban de tecnologia bancária 2025. Technical report, FEBRABAN.

Hamilton, W. L., Ying, R., and Leskovec, J. (2017). Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 1025–1035, Red Hook, NY, USA. Curran Associates Inc.

Hilal, W. et al. (2022). Financial fraud: A review of anomaly detection techniques and recent advances. IEEE Access.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9:1735–1780.

Hutchins, E. M., Cloppert, M. J., and Amin, R. M. Intelligence-driven computer network defense informed by analysis of adversary campaigns and intrusion kill chains. Leading Issues in Information Warfare & Security Research.

Lin, J., Guo, X., Zhu, Y., Mitchell, S., Altman, E., and Shun, J. (2024). Fraudgt: A simple, effective, and efficient graph transformer for financial fraud detection. In Proceedings of the 5th ACM International Conference on AI in Finance, ICAIF ’24, page 292–300, New York, NY, USA. Association for Computing Machinery.

Ma, R., Ma, Y., and Liu, X. (2025). Time series anomaly detection via temporal relationship graphs and adaptive smoothing. Applied Soft Computing, 179:113298.

Malhotra, P., Vig, L., Shroff, G., and Agarwal, P. (2015). Long short term memory networks for anomaly detection in time series.

Moloney, S. and Driehuis, E. (2023). The fraud kill chain. [link]. Accessed: 2026-03-20.

Motie, S. and Raahemi, B. (2024). Financial fraud detection using graph neural networks: A systematic review. Expert Systems with Applications, 240:122156.

Saldaña-Ulloa, D., De Ita Luna, G., and Marcial-Romero, J. R. (2024). A temporal graph network algorithm for detecting fraudulent transactions on online payment platforms. Algorithms, 17(12).

Schwartz, R., Dodge, J., Smith, N. A., and Etzioni, O. (2020). Green ai. Commun. ACM, 63(12):54–63.

Strom, B. E. et al. (2018). Mitre att&ck: Design and philosophy. Technical report, MITRE Corporation.

Strubell, E., Ganesh, A., and McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. In Korhonen, A., Traum, D., and Màrquez, L., editors, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3645–3650, Florence, Italy. Association for Computational Linguistics.

Wen, J., T. X.-L. J. (2024). An imbalanced learning method based on graph tran-smote for fraud detection. Sci Rep, 14.

Wu, J., Hu, R., Li, D., Ren, L., Hu, W., and Zang, Y. (2024). A gnn-based fraud detector with dual resistance to graph disassortativity and imbalance. Information Sciences, 669:120580.

Zioviris, G., Kolomvatsos, K., and Stamoulis, G. (2024). An intelligent sequential fraud detection model based on deep learning. Journal of Supercomputing, 80(10):14824 – 14847.