Method of blockchain-consensus distributed image classification

The study focuses on inter-node aggregation methods for model updates and local visual representations in distributed image classification systems. The paper aims to develop and experimentally validate a blockchain-consensus distributed image classification method that improves the robustness of the global model under heterogeneous, noisy, and partially malicious data sources. The proposed approach combines local class atlases, audit-based utility estimation of client updates, robust anomaly scoring of local trajectories, and blockchain-backed consensus weighting of node contributions. The blockchain layer is implemented as a reproducible software ledger for update provenance and audit logging. The experimental evaluation relies on the open CIFAR-10 and Olivetti Faces datasets in four scenarios: iid_clean, noniid_clean, noniid_noisy, and noniid_adversarial. The method is compared with Distributed Mean, Distributed Proximal, Distributed Trimmed Mean, and Atlas Consensus using Accuracy, Macro-F1, Balanced Accuracy, convergence dynamics, consensus weights, and statistical testing. The results show that the proposed method is not universally superior on clean distributions; however, in the target adversarial scenario it achieves the best performance among distributed schemes. The findings confirm the practical value of blockchain-consensus filtering of node updates for distributed visual data processing.

1. Kuzmitsky N.N. Convolutional neural model in a task of classification images of the isolated digits. Doklady BGUIR. 2012;(7):65–71. (In Russ.).

2. Firsov N.A., Podlipnov V.V., Ivliev N.A., et al. Ensembles of spectral-spatial convolutional neural network models for classifying soil types in hyperspectral images. Computer Optics. 2023;47(5):795–805. (In Russ.). https://doi.org/10.18287/2412-6179-CO-1260

3. Fedotov D.V. Using convolutional neural networks for solving problem of automated age estimation. Actual Problems of Aviation and Cosmonautics. 2015;1(11):377–379. (In Russ.).

4. Jumanov O.I. Adaptive neural network system for image visualization, recognition and classification of microobjects. The Herald of SibSUTIS. 2008;(2):76–85. (In Russ.).

5. Tashkov D.Yu., Ezhov I.E. Application of neural network algorithms for object recognition by image in security television systems. Almanac of the Perm Military Institute of the National Guard Troops. 2025;(1):95–106. (In Russ.).

6. Kuznetsov A.S., Semenov E.Y., Matrosova L.D. Image clustering using pretrained neural networks. International Journal of Open Information Technologies. 2019;7(7):42–47. (In Russ.).

7. Nazir S., Kaleem M. Federated Learning for Medical Image Analysis with Deep Neural Networks. Diagnostics. 2023;13(9):1532. https://doi.org/10.3390/diagnostics13091532

8. Touhami M., Ahmad Fauzi M.F., Ur Rehman Z., et al. Federated Learning for Histopathology Image Classification: A Systematic Review. Diagnostics. 2026;16(1):137. https://doi.org/10.3390/diagnostics16010137

9. Lee Sh.-M., Wu J.-L. FedUA: An Uncertainty-Aware Distillation-Based Federated Learning Scheme for Image Classification. Information. 2023;14(4):234. https://doi.org/10.3390/info14040234

10. Tang J., Ding X., Hu D., et al. FedRAD: Heterogeneous Federated Learning via Relational Adaptive Distillation. Sensors. 2023;23(14):6518. https://doi.org/10.3390/s23146518

11. Lv Y., Ding H., Wu H., et al. FedRDS: Federated Learning on Non-IID Data via Regularization and Data Sharing. Applied Sciences. 2023;13(23):12962. https://doi.org/10.3390/app132312962

12. Hsu H.-Y., Keoy K.H., Chen J.-R., et al. Personalized Federated Learning Algorithm with Adaptive Clustering for Non-IID IoT Data Incorporating Multi-Task Learning and Neural Network Model Characteristics. Sensors. 2023;23(22):9016. https://doi.org/10.3390/s23229016

13. Cha N., Chang L. Addressing Non-IID with Data Quantity Skew in Federated Learning. Information. 2025;16(10):861. https://doi.org/10.3390/info16100861

14. Khan K. FedEmerge: An Entropy-Guided Federated Learning Method for Sensor Networks and Edge Intelligence. Sensors. 2025;25(12):3728. https://doi.org/10.3390/s25123728

15. Ning W., Zhu Y., Song C., et al. Blockchain-Based Federated Learning: A Survey and New Perspectives. Applied Sciences. 2024;14(20):9459. https://doi.org/10.3390/app14209459

16. Lee J., Kim W. DAG-Based Blockchain Sharding for Secure Federated Learning with Non-IID Data. Sensors. 2022;22(21):8263. https://doi.org/10.3390/s22218263

17. Alghamdi A., Zhu J., Yin G., et al. Blockchain Empowered Federated Learning Ecosystem for Securing Consumer IoT Features Analysis. Sensors. 2022;22(18):6786. https://doi.org/10.3390/s22186786

18. Chen Zh., Li D., Zhu J., et al. DACFL: Dynamic Average Consensus-Based Federated Learning in Decentralized Sensors Network. Sensors. 2022;22(9):3317. https://doi.org/10.3390/s22093317

19. Zhao S., Zheng X., Chen J. Efficient Adversarial Training for Federated Image Systems: Crafting Client-Specific Defenses with Robust Trimmed Aggregation. Electronics. 2025;14(8):1541. https://doi.org/10.3390/electronics14081541

20. Yin X., Wu X., Zhang X. A Trusted Federated Learning Method Based on Consortium Blockchain. Information. 2025;16(1):14. https://doi.org/10.3390/info16010014

21. Zhu F., Hu F., Zhao Y., et al. A Secure and Fair Federated Learning Framework Based on Consensus Incentive Mechanism. Mathematics. 2024;12(19):3068. https://doi.org/10.3390/math12193068

22. Afanasyeva D.V., Abidarova A.A., Plahina E.A. Application of blockchain technology for digital identification of users. News of the Tula State University. Technical Sciences. 2019;(9):351–354. (In Russ.).

23. Tyurin A.V., Tyulyandin I.V., Maltsev V.S., et al. Overview of the Languages for Safe Smart Contract Programming. Proceedings of the Institute for System Programming of the RAS. 2019;31(3):157–176. https://doi.org/10.15514/ISPRAS-2019-31(3)-13

24. Afanasiev M.Ya., Fedosov Yu.V., Krylova A.A., et al. Organization of cyberphysical production systems using blockchain and smart-contracts technologies. Journal of Instrument Engineering. 2019;62(3):226–234. (In Russ.).