HashLearner: A Secure Decentralized Learning Framework Based on HashGraph

Mohammadi, Keyhan; Kozegar, Ehasan; Ebrahimi Atani, Reza

doi:10.22042/isecure.2026.242015

HashLearner: A Secure Decentralized Learning Framework Based on HashGraph

Articles in Press

Document Type : Research Article

Authors

Keyhan Mohammadi ¹

Ehasan Kozegar ²

Reza Ebrahimi Atani ¹

¹ Department of Computer Engineering, Faculty of Engineering, University of Guilan, Rasht, Iran

² Department of Computer Engineering, Faculty of Technology and Engineering-East of Guilan, University of Guilan, Rudsar, Guilan, Iran

10.22042/isecure.2026.242015

Abstract

Federated learning enables collaborative model training without centralized data collection, but existing frameworks rely on a central server, introducing risks of single points of failure, adversarial manipulation, and privacy leakage. To address these challenges, we propose HashLearner, a secure decentralized learning framework that utilizes the HashGraph consensus protocol for model aggregation without trusted authorities. HashLearner introduces two key innovations: (i) a consensus-driven decentralized aggregation mechanism resilient to Byzantine adversaries, and (ii) a privacy-preserving shuffling strategy that mitigates gradient reconstruction and poisoning attacks. To handle heterogeneous data distributions, the framework further employs transfer learning–based personalization. The simulation results of HashLearner, tested on benchmark Kaggle datasets, demonstrate that the platform maintains high accuracy while significantly enhancing scalability, security, and privacy. These findings indicate that HashLearner provides a practical path toward scalable, privacy-preserving, and trustworthy decentralized federated learning.

Keywords

Federated Learning

HashGraph

Decentralized Learning

Security

Privacy

Machine Learning

[1] Jakub Konečný, H. Brendan McMahan, Felix X. Yu, Peter Richtárik, Ananda Theertha Suresh, and Dave Bacon. Federated learning: Strategies for improving communication efficiency, 2017. URL https://arxiv.org/abs/1610.05492.

[2] Li Li, Yuxi Fan, Mike Tse, and Kuo-Yi Lin. A review of applications in federated learning. Computers & Industrial Engineering, 149:106854, 2020. ISSN 0360-8352. . URL https://www.sciencedirect.com/ science/article/pii/S0360835220305532.

[3] Shui Yu and Lei Cui. Security and Privacy in Federated Learning. Springer, 2023.

[4] Keyhan Mohammadi and Reza Ebrahimi Atani. Sigma: A secure federated network gaming platform. In 2024 15th International Conference on Information and Knowledge Technology (IKT), pages 222–227, 2024.

[5] Yiqiang Chen, Xin Qin, Jindong Wang, Chaohui Yu, and Wen Gao. Fedhealth: A federated transfer learning framework for wearable healthcare. IEEE Intelligent Systems, 35(4):83–93, 2020.

[6] Márk Jelasity, Spyros Voulgaris, Rachid Guerraoui, Anne-Marie Kermarrec, and Maarten van Steen. Gossip-based peer sampling. ACM Trans. Comput. Syst., 25(3):8–es, August 2007. ISSN 0734-2071. . URL https://doi.org/10.1145/ 1275517.1275520.

[7] Alexandre Pham, Maria Potop-Butucaru, Sébastien Tixeuil, and Serge Fdida. Data poisoning attacks in gossip learning, 2024. URL https://arxiv.org/abs/2403.06583.

[8] Wael Issa, Nour Moustafa, Benjamin Turnbull, Nasrin Sohrabi, and Zahir Tari. Blockchainbased federated learning for securing internet of things: A comprehensive survey. ACM Comput. Surv., 55(9), January 2023. ISSN 0360-0300. . URL https://doi.org/10.1145/3560816.

[9] Leemon Baird. The swirlds hashgraph consensus algorithm: Fair, fast, byzantine fault tolerance. Swirlds Tech Reports SWIRLDS-TR-201601, Tech. Rep, 34:9–11, 2016.

[10] Zhilin Wang, Qin Hu, Minghui Xu, Yan Zhuang, Yawei Wang, and Xiuzhen Cheng. A systematic survey of blockchained federated learning, 2024. URL https://arxiv.org/abs/2110.02182.

[11] Dun Li, Dezhi Han, Tien-Hsiung Weng, Zibin Zheng, Hongzhi Li, Han Liu, Arcangelo Castiglione, and Kuan-Ching Li. Blockchain for federated learning toward secure distributed machine learning systems: a systemic survey. Soft Computing, 26(9):4423–4440, 2022.

[12] Dinh C. Nguyen, Ming Ding, Quoc-Viet Pham, Pubudu N. Pathirana, Long Bao Le, Aruna Seneviratne, Jun Li, Dusit Niyato, and H. Vincent Poor. Federated learning meets blockchain in edge computing: Opportunities and challenges, 2021. URL https://arxiv.org/abs/ 2104.01776.

[13] Rafael Barbarroxa, João Silva, Luis Gomes, Fernando Lezama, Bruno Ribeiro, and Zita Vale. Fedis: Federated learning framework supported by distributed ledger. In Blockchain and Applications, 5th International Congress, pages 32–41. Springer Nature Switzerland, 2023.

[14] Yongding Tian, Zhuoran Guo, Jiaxuan Zhang, and Zaid Al-Ars. Dfl: High-performance blockchain-based federated learning. Distrib. Ledger Technol., 2(3), September 2023. . URL https://doi.org/10.1145/3600225.

[15] Hiroki Kaminaga, Feras M. Awaysheh, Sadi Alawadi, and Liina Kamm. Mpcfl: Towards multi-party computation for secure federated learning aggregation. In Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing, UCC ’23, New York, NY, USA, 2024. Association for Computing Machinery. ISBN 9798400702341. URL https://doi.org/10.1145/3603166. 3632144.

[16] Saba Ameri and Reza Ebrahimi Atani. A novel decentralized privacy preserving federated learning model for healthcare application. In 2024 15th International Conference on Information and Knowledge Technology (IKT), pages 115– 120, 2024.

[17] István Hegedűs, Gábor Danner, and Márk Jelasity. Gossip learning as a decentralized alternative to federated learning. In José Pereira and Laura Ricci, editors, Distributed Applications and Interoperable Systems, pages 74–90, Cham, 2019. Springer International Publishing. ISBN 978-3-030-22496-7.

[18] Roberto Roverso, Jim Dowling, and Mark Jelasity. Through the wormhole: Low cost, fresh peer sampling for the internet. In IEEE P2P 2013 Proceedings, pages 1–10, 2013.

[19] Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge L. Reyes-Ortiz. Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In José Bravo, Ramón Hervás, and Marcela Rodríguez, editors, Ambient Assisted Living and Home Care, pages 216–223, Berlin, Heidelberg, 2012. Springer Berlin Heidelberg. ISBN 978-3642-35395-6.

[20] Keyhan Mohammadi, Reza Ebrahimi Atani. HashLearner, 2025. URL https://github.com/ cosmopole-org/hash-learner. Accessed on 2025-04-01.

[21] Ligeng Zhu, Zhijian Liu, and Song Han. Deep leakage from gradients, 2019. URL https:// arxiv.org/abs/1906.08935.

[22] Privacy-preserving in blockchain-based federated learning systems. Computer Communications, 222:38–67, 2024. ISSN 0140-3664.