Logo PTI Logo FedCSIS

Position Papers of the 21st Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 48

Anomaly Detection with a Blockchain Audit Trail for Open Banking Anti-Fraud: Prototype Evidence and Research Agenda

DOI: http://dx.doi.org/10.15439/2026F1099

Citation: Krzysztof Piech (). Anomaly Detection with a Blockchain Audit Trail for Open Banking Anti-Fraud: Prototype Evidence and Research Agenda. In M. Bolanowski, M. Ganzha, M. Grzegorowski, L. Maciaszek, M. Paprzycki, A. Paszkiewicz, D. Ślęzak (eds), Proceedings of the 21st Conference on Computer Science and Intelligence Systems. ACSIS, Vol. 48, pages 197–204.

Full text

Abstract. This paper presents preliminary prototype evidence from an industrial research project on an Open Banking Anti-Fraud PSD2 system. The proposed approach combines anomaly detection based on customer-behaviour-relative features with a blockchain-based audit trail. The system was designed to address three practical challenges in PSD2/Open Banking environments: real-time fraud screening, reduction of false positives, and auditable recording of monitoring activities. The prototype integrates transaction and customer-context data from a European payment institution with an anomaly-detection layer and a permissioned blockchain component used to preserve tamper-evident records of analytical actions and results. More than 30 input features were developed. Prototype evidence suggests that customer-behaviour-relative features improved discrimination relative to absolute features, with AUC increasing from 0.939 to 0.996 in the reported comparison. The final anomaly-detection model supported sub-second operational scoring, while a simulated cross-institution feature-sharing procedure completed in approximately 10.3 seconds. The paper also clarifies the validation scope: the anomaly-detection results are preliminary and internally evaluated, whereas broader production-level validation remains future work. The contribution of the paper is twofold. First, it proposes an information-systems architecture linking AI-based anomaly detection, explainable scoring, and blockchain-supported auditability. Second, it formulates a research agenda for validating such systems across institutions, datasets, and regulatory settings.

References

  1. Directive (EU) 2015/2366 of the European Parliament and of the Council of 25 November 2015 on payment services in the internal market, OJ L 337, 23.12.2015, pp. 35–127. ELI: http://data.europa.eu/eli/dir/2015/2366/oj.
  2. M. Gounari, G. Stergiopoulos, K. Pipyros, et al., “Harmonizing open banking in the European Union: an analysis of PSD2 compliance and interrelation with cybersecurity frameworks and standards,” International Cybersecurity Law Review, vol. 5, pp. 79–120, 2024, https://dx.doi.org/10.1365/s43439-023-00108-8.
  3. E. W. T. Ngai, Y. Hu, Y. H. Wong, Y. Chen, and X. Sun, “The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature,” Decision Support Systems, vol. 50, no. 3, pp. 559–569, 2011, https://dx.doi.org/10.1016/j.dss.2010.08.006.
  4. A. Dal Pozzolo, O. Caelen, Y.-A. Le Borgne, S. Waterschoot, and G. Bontempi, “Learned lessons in credit card fraud detection from a practitioner perspective,” Expert Systems with Applications, vol. 41, no. 10, pp. 4915–4928, 2014, https://dx.doi.org/10.1016/j.eswa.2014.02.026.
  5. H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263–1284, 2009, https://dx.doi.org/10.1109/TKDE.2008.239.
  6. V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: A survey,” ACM Computing Surveys, vol. 41, no. 3, Article 15, 2009, https://dx.doi.org/10.1145/1541880.1541882.
  7. F. T. Liu, K. M. Ting, and Z.-H. Zhou, “Isolation Forest,” in Proceedings of the 2008 IEEE International Conference on Data Mining, Pisa, Italy, 2008, pp. 413–422, https://dx.doi.org/10.1109/ICDM.2008.17.
  8. B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson, “Estimating the support of a high-dimensional distribution,” Neural Computation, vol. 13, no. 7, pp. 1443–1471, 2001, https://dx.doi.org/10.1162/089976601750264965.
  9. M. M. Breunig, H.-P. Kriegel, R. T. Ng, and J. Sander, “LOF: Identifying density-based local outliers,” in Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, Dallas, TX, USA, 2000, pp. 93–104, https://dx.doi.org/10.1145/342009.335388.
  10. S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems 30 (NeurIPS 2017), 2017, pp. 4765–4774.
  11. M. Esche, L. Ho, M. Nischwitz, and S. Glesner, “Practical security of evidence for regulated artificial intelligence modules,” Annals of Computer Science and Information Systems, vol. 44, pp. 23–30, 2025, https://dx.doi.org/10.15439/2025F4971.
  12. B. Schneier and J. Kelsey, “Secure audit logs to support computer forensics,” ACM Transactions on Information and System Security, vol. 2, no. 2, pp. 159–176, 1999, https://dx.doi.org/10.1145/317087.317089.
  13. B. Putz, F. Menges, and G. Pernul, “A secure and auditable logging infrastructure based on a permissioned blockchain,” Computers & Security, vol. 87, Article 101602, 2019, https://dx.doi.org/10.1016/j.cose.2019.101602.
  14. Igoria Trade S.A., “Research and development work on an Open Banking Anti-Fraud PSD2 system based on blockchain technology and machine learning in transaction monitoring and fraud detection processes – project assumptions from the grant application,” internal project document, 2020.
  15. Igoria Trade S.A., “Open Banking Anti Fraud PSD2 Report: Stage 3 – Anti-Fraud System,” internal R&D report, 2023.
  16. Igoria Trade S.A., “Open Banking Anti Fraud PSD2 Report: Stage 5 – Technical architecture, implementation and deployment documentation,” internal R&D report, draft, 2023.
  17. W. Kuliński and K. Piech, “Blockchain oraz uczenie maszynowe w identyfikowaniu oszustw finansowych,” in Kompendium Blockchain. Zagadnienia prawne rynku kryptoaktywów, K. Piech, G. Sobiecki, and W. Srokosz, Eds. Gliwice, Poland: Wydawnictwo Naukowe Helion, 2026, ISBN 978-83-289-0664-8, forthcoming.
  18. W. Kuliński, “Computer-aided method of making settlements by banks and other financial institutions, computer-aided method of assessing the risk of transactions made by banks or other banking institutions and a durable data carrier,” Polish patent application P.435406, filed Sept. 22, 2020, published Mar. 28, 2022. Applicant: Igoria Trade S.A.; status: pending.