Skip to main content
SpringerLink
Log in

Robust Cross-Silo Federated Fraudulent Transaction Detection in Banks Using Epsilon Cluster Selection

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Fraudulent transaction detection in a bank is a highly imbalanced classification problem. In addition, one single bank will not have a wide variety of different fraudulent transactions in its database to learn from. Collaboration between banks is needed to achieve an effective model, but banks do not share their data with each other due to competition and regulatory restrictions. Federated learning can be leveraged here to solve this problem. Here, the data held by different banks will be different in terms of distribution and hence follows a non-IID scenario across the participants’ datasets. Moreover, we assume that a minority of the banks could be malicious and will try to disrupt the federated learning process. Hence, the problem is to perform federated learning in a non-IID cross-silo setting with active adversaries involved. For this, we propose a novel algorithm—Epsilon Cluster Selection, a filter-based aggregation technique to recognize and prevent malicious nodes from contributing to the global model being trained. We apply this algorithm to this setting with malicious banks and compare the results. Furthermore, we consider additional attack scenarios featuring more stealthier attacks like only using a part of the data for attacks as well as keeping malicious banks benign for a part of training time to assess the resilience of our algorithm by varying the levels of maliciousness within a bank.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability statement

We are not sharing any code/data at present.

Notes

  1. This paper is a continuation of our work from Robust Collaborative Fraudulent Transaction Detection using Federated Learning [13] presented at ICMLA 2021.

References

  1. Japkowicz N, Stephen S. The class imbalance problem: a systematic study. Intell Data Anal. 2002;6(5):429–49.

    Article  MATH  Google Scholar 

  2. Lopez-Rojas EA, Elmir A, Axelsson S. “PaySim: A financial mobile money simulator for fraud detection”. In: The 28th European Modeling and Simulation Symposium-EMSS, Larnaca, Cyprus. 2016

  3. McMahan HB, Moore E, Ramage D, Hampson S, y Arcas BA. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017. JMLR: W &CP.2017;54

  4. Kairouz P, McMahan HB. Advances and open problems in federated learning. Found Trends® Mach Learn. 2021. https://doi.org/10.1561/2200000083.

    Article  MATH  Google Scholar 

  5. Zhao Y, Li M, Lai L, Suda N, Civin D, Chandra V. Federated learning with non-iid data. arXiv preprint arXiv:1806.00582. 2018.

  6. Blanchard P, El Mhamdi EM, Guerraoui R, Stainer J. Machine learning with adversaries: Byzantine tolerant gradient descent. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R. (eds.) Advances in Neural Information Processing Systems, Curran Associates, Inc., ??? 2017;30.

  7. Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems. 2020;2:429–50.

  8. Wang J, Liu Q, Liang H, Joshi G, Poor HV. Tackling the objective inconsistency problem in heterogeneous federated optimization. Adv Neural Inf Process Syst. 2020;33:7611–23.

  9. Chen X, Liu C, Li B, Lu K, Song D. Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526. 2017 Dec 15.

  10. Li S, Cheng Y, Liu Y, Wang W, Chen T. Abnormal client behavior detection in federated learning. arXiv preprint arXiv:1910.09933. 2019 Oct 22.

  11. Tolpegin V, Truex S, Gursoy ME, Liu L. Data poisoning attacks against federated learning systems. InComputer Security–ESORICS 2020: 25th European Symposium on Research in Computer Security, ESORICS 2020, Guildford, UK, September 14–18, 2020, Proceedings, Part I 25 2020 (pp. 480–501). Springer International Publishing.

  12. Yu L, Wu L. Towards byzantine-resilient federated learning via group-wise robust aggregation. 2020:81–92. https://doi.org/10.1007/978-3-030-63076-8_6

  13. Myalil D, Rajan MA, Apte M, Lodha S. Robust collaborative fraudulent transaction detection using federated learning. In: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA). 2021: 373–8. https://doi.org/10.1109/ICMLA52953.2021.00064

  14. Weber M, Chen J, Suzumura T, Pareja A, Ma T, Kanezashi H, Kaler T, Leiserson CE, Schardl TB. Scalable graph learning for anti-money laundering: A first look. arXiv preprint arXiv:1812.00076. 2018 Nov 30.

  15. Mubalaike AM, Adali E. Deep learning approach for intelligent financial fraud detection system. In: 2018 3rd International Conference on Computer Science and Engineering (UBMK). 2018:598–603. https://doi.org/10.1109/UBMK.2018.8566574

  16. Roy A, Sun J, Mahoney R, Alonzi L, Adams S, Beling P. Deep learning detecting fraud in credit card transactions. In: 2018 Systems and Information Engineering Design Symposium (SIEDS).2018:129–34. https://doi.org/10.1109/SIEDS.2018.8374722

  17. Lebichot B, Le Borgne Y-A, He-Guelton L, Oblé F, Bontempi G. Deep-learning domain adaptation techniques for credit cards fraud detection. In: Oneto L, Navarin N, Sperduti A, Anguita D, editors. Recent advances in big data and deep learning. Cham: Springer; 2020. p. 78–88.

    Chapter  Google Scholar 

  18. Kazemi Z, Zarrabi H. Using deep networks for fraud detection in the credit card transactions. In: 2017 IEEE 4th International Conference on Knowledge-Based Engineering and Innovation (KBEI). 2017:0630–3. https://doi.org/10.1109/KBEI.2017.8324876

  19. Yang W, Zhang Y, Ye K, Li L, Xu CZ. Ffd: A federated learning based method for credit card fraud detection. InBig Data–BigData 2019: 8th International Congress, Held as Part of the Services Conference Federation, SCF 2019, San Diego, CA, USA, June 25–30, 2019, Proceedings 8 2019 (pp. 18–32). Springer International Publishing.

  20. Huang Y, Chu L, Zhou Z, Wang L, Liu J, Pei J, Zhang Y. Personalized Cross-Silo federated learning on non-IID data. In: press: 2021.

  21. Li Q, Diao Y, Chen Q, He B. Federated learning on non-IID data silos: an experimental study. https://doi.org/10.48550/ARXIV.2102.02079. https://arxiv.org/abs/2102.02079

  22. Li Q, He B, Song D. Practical one-shot federated learning for cross-silo setting:2021. arXiv: Learning

  23. Zhang C, Li S, Xia J, Wang W, Yan F, Liu Y. Batchcrypt: efficient homomorphic encryption for cross-silo federated learning. In: 2020 USENIX Annual Technical Conference (USENIX ATC 20), USENIX Association, ???. 2020:493–506.

  24. Wang H, Yurochkin M, Sun Y, Papailiopoulos D, Khazaeni Y. Federated learning with matched averaging:2020. arXiv preprint arXiv:2002.06440

  25. Wang H, Kaplan Z, Niu D, Li B. Optimizing federated learning on non-iid data with reinforcement learning. In: IEEE INFOCOM 2020 - IEEE Conference on Computer Communications.2020:1698–707.

  26. Sattler F, Wiedemann S, Müller K-R, Samek W. Robust communication-efficient federated learning from non-i.i.d. data. IEEE Trans Neural Netw Learn Syst. 2020;31(9):3400–13. https://doi.org/10.1109/TNNLS.2019.2944481.

    Article  MathSciNet  Google Scholar 

  27. Yue K, Jin R, Pilgrim R, Wong C-W, Baron D, Dai H. Neural tangent kernel empowered federated learning:2021 arXiv. https://doi.org/10.48550/ARXIV.2110.03681arxiv:2110.03681

  28. Fung C, Yoon CJ, Beschastnikh I. Mitigating sybils in federated learning poisoning. arXiv preprint arXiv:1808.04866. 2018 Aug 14.

  29. Chen Y, Yang X, Qin X, Yu H, Chan P, Shen Z. Dealing with label quality disparity in federated learning. Fed Learn Priv Incent. 2020:108–21.

  30. Goldreich O. Foundations of cryptography: volume 2, basic applications. Cambridge university press; 2009 Sep 17.

  31. Rousseeuw P, Rousseeuw PJ. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math. 1987;20:53–65. https://doi.org/10.1016/0377-0427(87)90125-7.

    Article  MATH  Google Scholar 

  32. MacQueen J. Classification and analysis of multivariate observations. In5th Berkeley Symp. Math. Statist. Probability 1967 Jun 21 (pp. 281–297). Los Angeles LA USA: University of California.

  33. Davies DL, Bouldin DW. A cluster separation measure. IEEE Trans Pattern Anal Mach Intell PAMI-1. 1979. https://doi.org/10.1109/TPAMI.1979.4766909.

    Article  Google Scholar 

  34. Ryffel T, Trask A, Dahl M, Wagner B, Mancuso J, Rueckert D, Passerat-Palmbach J. A generic framework for privacy preserving deep learning.(2018). arXiv preprint arXiv:1811.04017. 2018.

  35. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770–778).

  36. Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Teh YW, Titterington M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research. 2010;9:249–256. PMLR, Chia Laguna Resort, Sardinia, Italy.

  37. Mohassel P, Zhang Y. Secure ml: a system for scalable privacy-preserving machine learning. In: 2017 IEEE Symposium on Security and Privacy (SP).2017:19–38. https://doi.org/10.1109/SP.2017.12

Download references

Funding

The authors declare that they have received no funding.

Author information

Authors and Affiliations

  1. TCS Research, Tata Consultancy Services, Bengaluru, India

    Delton Myalil, M. A. Rajan, Manoj Apte & Sachin Lodha

Authors
  1. Delton Myalil
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. A. Rajan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Manoj Apte
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sachin Lodha
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Research problem identification: MAR, MA; research approach definition: DM, MAR, MA; development and coding: DM; main manuscript text and review: DM, MAR, MA, SL.

Corresponding author

Correspondence to Delton Myalil.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Myalil, D., Rajan, M.A., Apte, M. et al. Robust Cross-Silo Federated Fraudulent Transaction Detection in Banks Using Epsilon Cluster Selection. SN COMPUT. SCI. 4, 422 (2023). https://doi.org/10.1007/s42979-023-01873-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-023-01873-3

Keywords

Search

Navigation