Abstract

Federated Learning (FL) is one of the potentially useful paradigms of collaborative machine learning, where various clients compute their models independently on their private data, while preserving privacy. However, FL in particular suffers from transparency, auditing and traceability issues, one of the key requirements to ensure reliability and trust in the global model.This paper proposes a federated learning system auditing and traceability framework based on blockchain. Each client trains a CNN on their data and updates the model, those updates are securely hashed, written to a blockchain and attached to metadata including the identity of the client, local accuracy and time. It is a way of assurance and responsibility, in which all contribution of clients is monitored accurately while training process. The global model is trained using an iterative model convergence process called federated averaging (FedAvg) that merges the input of the clients without sacrificing privacy. Empirical experiments on MNIST data set demonstrate competitive classification accuracy and transparent and tamper-proof auditing of model updates. The findings suggest that using blockchain technology in federated learning not just boosts security and accountability, but also increases traceability, and is therefore applicable to real-world applications of decentralized AI where trust and reliability are paramount.

References

• H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” Jan. 2023.
• Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated Machine Learning,” ACM Trans. Intell. Syst. Technol., vol. 10, no. 2, pp. 1–19, Mar. 2019, doi: 10.1145/3298981.
• D. C. Nguyen, M. Ding, and Q. V. Pham, “ederated Learning Meets Blockchain in Privacy-Preserving Wireless Networks: A Survey,” IEEE Communications Surveys & Tutorials, vol. 24, no. 1, pp. 105–143, 2022.
• P. Kairouz et al., “Advances and Open Problems in Federated Learning,” Mar. 2021.
• T. K. Rodrigues, J. Liu, and Y. Kato, “Blockchain-Based Auditing Layers for Mitigating Poisoning Attacks in Decentralized Machine Learning,” IEEE Trans. Dependable Secure Comput., vol. 22, no. 4, pp. 1820–1834, 2025.
• E. Bagdasaryan, A. Veit, Y. Hua, D. Estrin, and V. Shmatikov, “How To Backdoor Federated Learning,” Aug. 2019.
• C. S. Wright, “Bitcoin: A Peer-to-Peer Electronic Cash System,” SSRN Electronic Journal, 2008, doi: 10.2139/ssrn.3440802.
• Y. Lu, “The blockchain: State-of-the-art and research challenges,” J. Ind. Inf. Integr., vol. 15, pp. 80–90, Sep. 2019, doi: 10.1016/j.jii.2019.04.002.
• Y. J. Kim and C. S. Hong, “BlockFL: Blockchain-based Federated Learning for Robust and Verifiable AI Ecosystems,” IEEE Access, vol. 11, pp. 24510–24525, 2023.
• M. Al-Rubaie and J. M. Chang, “Privacy-Preserving Machine Learning: Threats and Solutions,” IEEE Secur. Priv., vol. 17, no. 2, pp. 49–58, Mar. 2019, doi: 10.1109/MSEC.2018.2888775.
• L. U. Khan, W. Saad, Z. Han, and C. S. Hong, “Blockchain for Federated Learning: Requirements, Challenges, and Future Directions,” IEEE Signal Process. Mag., vol. 38, no. 3, pp. 135–142, 2021.
• X. Wang et al., “Securing Federated Learning With Blockchain in the Medical Field: Systematic Literature Review,” J. Med. Internet Res., vol. 28, pp. e79052–e79052, Feb. 2026, doi: 10.2196/79052.
• N. Romandini, A. Roberta Costagliola, A. Bujari, and R. Montanari, “TrustFLow: A traceable federated learning framework to enable trustworthy digital twins,” Future Generation Computer Systems, vol. 178, p. 108267, May 2026, doi: 10.1016/j.future.2025.108267.
• T. Muazu and M. Yingchi, “Blockchain-Enabled federated learning framework with cantor filtering and reed–Solomon coding for secure healthcare IoT systems,” Computer Networks, vol. 280, p. 112161, May 2026, doi: 10.1016/j.comnet.2026.112161.
• Z. Cui, X. Zhang, and S. Zhou, “Enhancing network monitoring in IoT with an energy-efficient collaborative framework using edge computing and federated learning,” Expert Syst. Appl., vol. 318, p. 132034, Jul. 2026, doi: 10.1016/j.eswa.2026.132034.
• B. M. Yakubu, N. S. M. Jamail, R. Latif, and S. Latif, “Secured-FL: Blockchain-Based Defense against Adversarial Attacks on Federated Learning Models,” Computers, Materials & Continua, vol. 0, no. 0, pp. 1–10, 2025, doi: 10.32604/cmc.2025.072426.
• J. Liu et al., “Enhancing trust and privacy in distributed networks: a comprehensive survey on blockchain-based federated learning,” Knowl. Inf. Syst., vol. 66, no. 8, pp. 4377–4403, Aug. 2024, doi: 10.1007/s10115-024-02117-3.
• GV. Shrichandran et al., “Energy-efficient multi-agent hybrid GNN-XGBoost framework for IoT-enabled smart grid management with blockchain-secured urban energy sustainability,” Sustainable Computing: Informatics and Systems, vol. 50, p. 101338, Jun. 2026, doi: 10.1016/j.suscom.2026.101338.
• B. B. Sezer, H. Turkmen, and U. Nuriyev, “PPFchain: A novel framework privacy-preserving blockchain-based federated learning method for sensor networks,” Internet of Things, vol. 22, p. 100781, Jul. 2023, doi: 10.1016/j.iot.2023.100781.
• P. Kumar and B. Dezfouli, “quicSDN: Transitioning from TCP to QUIC for southbound communication in software-defined networks,” Journal of Network and Computer Applications, vol. 222, p. 103780, Feb. 2024, doi: 10.1016/j.jnca.2023.103780.
• S. Al-E’mari, Y. Sanjalawe, and S. Fraihat, “Detection of obfuscated Tor traffic based on bidirectional generative adversarial networks and vision transform,” Comput. Secur., vol. 135, p. 103512, Dec. 2023, doi: 10.1016/j.cose.2023.103512.
• M. Aftowicz, I. Kabin, Z. Dyka, and P. Langendörfer, “Non-Profiled Unsupervised Horizontal Iterative Attack against Hardware Elliptic Curve Scalar Multiplication Using Machine Learning,” Future Internet, vol. 16, no. 2, p. 45, Jan. 2024, doi: 10.3390/fi16020045.
• M. Abadi and A. Agarwal, “TensorFlow: A system for large-scale machine learning,” in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2016, pp. 265–283.
• Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998, doi: 10.1109/5.726791.
• A. M. El-Sawy, M. K. Mahmoud, and N. A. Eldin, “Evaluating Convolutional Neural Networks under Non-IID Data Splits in Federated Learning Environments,” Pattern Recognit. Lett., vol. 174, pp. 88–95, 2024.
• A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, May 2017, doi: 10.1145/3065386.
• F. Chollet, Deep learning with Python. Manning, 2018.
• J. W. Hassan, S. T. Al-Ahmadi, and R. O. Mohamed, “A Review of Decentralized AI Frameworks: Balancing Computational Overhead and Structural Traceability,” Artif. Intell. Rev., vol. 59, no. 1, pp. 112–135, 2025.
• X. Wang, “Consensus Mechanisms in Blockchain-enabled Federated Learning for Healthcare IoT,” IEEE Internet Things J., vol. 11, no. 4, pp. 5432–5445, 2024.
• R. H. Badr, “Privacy-Preserving Deep Learning: Systematic Review on Secure Model Aggregation,” Decentralized AI Review, vol. 4, no. 2, pp. 201–215, 2025.