Application of machine learning algorithms to enhance blockchain network security

2024;
: pp. 893–903
https://doi.org/10.23939/mmc2024.03.893
Received: April 24, 2024
Revised: September 25, 2024
Accepted: September 26, 2024

Solomka I. R., Liubinskyi B. B., Torshyn V. V.  Application of machine learning algorithms to enhance blockchain network security.  Mathematical Modeling and Computing. Vol. 11, No. 3, pp. 893–903 (2024)

1
Lviv Polytechnic National University
2
Lviv Polytechnic National University
3
Lviv Polytechnic National University

This paper embarks on a detailed examination of the inherent security challenges faced by blockchain networks, including fraudulent transactions, double-spending, and 51% attacks, among others.  Using recent advancements in ML, it presents a novel methodology for real-time anomaly detection, predictive threat modeling, and adaptive security protocols that leverage data-driven insights to fortify the blockchain against both known and emerging threats.  By analyzing case studies and empirical data, this study illustrates the effectiveness of ML techniques in enhancing the resilience and integrity of blockchain systems.  Furthermore, it explores the implications of these innovations for future blockchain applications, proposing a framework for the integration of ML into blockchain security strategies.  This article aims to serve as a cornerstone for researchers, technologists, and cybersecurity professionals, offering insights into the future of secure blockchain ecosystems powered by the intelligent capabilities of machine learning.

  1. Nakamoto S.  Bitcoin: A Peer-to-Peer Electronic Cash System (2008).
  2. King S., Nadal S.  PPCoin: Peer-to-Peer Crypto-Currency with Proof-of-Stake (2012).
  3. Charts B.  Bitcoin network.  http://bitcoincharts.com/bitcoin/ (2024).
  4. Douceur J. R.  The Sybil Attack.  Peer-to-Peer Systems. 251–260 (2002).
  5. Eyal I., Sirer E. G.  Majority is not enough: Bitcoin mining is vulnerable.  Communications of the ACM.  61 (7), 95–102 (2018).
  6. Mt. Gox Hack – The Most Iconic Exchange Hack, Blockonomi.  https://blockonomi.com/mt-gox-hack/ (2024).
  7. Weichbroth P., Wereszko K., Anacka H., Kowal J.  Security of Cryptocurrencies: A View on the State-of-the-Art Research and Current Developments.  Sensors.  23 (6), 3155 (2023).
  8. Apostolaki M., Zohar A., Vanbever L.  Hijacking Bitcoin: Routing Attacks on Cryptocurrencies.  2017 IEEE Symposium on Security and Privacy.  375–392 (2017).
  9. Eskandari S., Barrera D., Stobert E., Clark J.  A First Look at the Usability of Bitcoin Key Management.  Workshop on Usable Security (2015).
  10. Atzei N., Bartoletti M., Cimoli T.  A Survey of Attacks on Ethereum Smart Contracts (SoK).  Principles of Security and Trust. 164–186 (2017).
  11. Buterin V.  A Next-Generation Smart Contract and Decentralized Application Platform.  https://github.com/ethereum/wiki/wiki/White-Paper (2017).
  12. Zohar A.  Bitcoin: under the hood.  Communications of the ACM.  58 (9), 104–113 (2015).
  13. Unger N., Dechand S., Bonneau J., Fahl S., Perl H., Goldberg I., Smith M.  SoK: Secure Messaging.  2015 IEEE Symposium on Security and Privacy.  232–249 (2015).
  14. Kiayias A., Russell A., David B., Oliynykov R.  Ouroboros: A Provably Secure Proof-of-Stake Blockchain Protocol.  Advances in Cryptology – CRYPTO 2017.  357–388 (2017).
  15. Kuhn M., Johnson K.  Nonlinear classification models.  In: M. Kuhn, K. Johnson (eds).  Applied Predictive Modeling.  New York, Springer (2013).
  16. Han J., Kamber M., Pei J.  Data Mining: Concepts and Techniques.  Book, Third Edition (2012).
  17. Chen B., Liu Y., Zhang C., Wang Z.  Time Series Data for Equipment Reliability Analysis With Deep Learning.  IEEE Access.  8, 105484–105493 (2020).
  18. Zhang X., Li X., Feng Y., Liu Z.  The use of ROC and AUC in the validation of objective image fusion metrics.  Signal Processing.  115, 38–48 (2015).
  19. Fawcett T.  An introduction to ROC analysis.  Pattern Recognition Letters.  27 (8), 861–874 (2006).