A Hybrid Encryption Medical Information Security Collaboration Scheme Based on Blockchain and Federated Learning
Abstract
In current medical data sharing practices, the tension between data privacy protection and cross-institutional collaboration efficiency has become increasingly prominent. To address existing security challenges in healthcare data sharing, we propose a collaborative data cooperation model based on blockchain and federated learning, Through federated learning technology, data is made “usable but not visible” by enabling medical institutions to share only encrypted model parameters, thereby preventing the leakage of raw data. Meanwhile, blockchain technology is introduced to establish a decentralized trust mechanism, utilizing smart contracts to automate data access management and track training processes. In addition, the dual security protection strategy is designed, where differential privacy and Paillier homomorphic encryption technology are adopted to resist member reasoning attacks and ensure secure storage and sharing of information. Through security analysis and experimental validation, the scheme has been proven to have good security and usability.
References
Li Y, Li Z, Li Q, et al., 2025, A Searchable Cryptographic Electronic Medical Record Sharing Scheme in Blockchain. Computer Engineering and Science, 47(8): 1399–1407.
Zhang M, Gu C, Zhang Y, et al., 2025, Privacy Protection Scheme for Blockchain Federated Learning Based on Dynamic Group Signatures. Computer Application Research, 42(11): 1–8.
Kim H, Park J, Bennis M, et al., 2020, Blockchained On-Device Federated Learning. IEEE Communications Letters, 24(6): 1279–1283.
Majeed U, Khan L, Yousafzai A, et al., 2021, St-bfl: A Structured Transparency Empowered Cross-Silo Federated Learning on the Blockchain Framework. IEEE Access, 2021(9): 155634–155650.
Zhang H, Li G, Zhang Y, et al., 2021, Blockchain-Based Privacy-Preserving Medical Data Sharing Scheme using Federated Learning. International Conference on Knowledge Science, Engineering and Management, 634–646.
Qu Y, Gao L, Luan T, et al., 2020, Decentralized Privacy using Blockchain-Enabled Federated Learning in Fog Computing. IEEE Internet of Things Journal, 7(6): 5171–5183.
Zeng S, Huo R, Huang T, et al., 2020, Survey of Blockchain: Principle, Progress and Application. Journal on Communications, 41(1): 134–151.
Zhang Q, Ding Q, Zhu J, et al., 2021, Blockchain Empowered Reliable Federated Learning by Worker Selection: A Trustworthy Reputation Evaluation Method. IEEE Wireless Communications and Networking Conference Workshops (WCNCW), 1–6.
Wang Q, Guo Y, Wang X, et al., 2020, AI at the Edge: Blockchain-Empowered Secure Multiparty Learning with Heterogenous Models. IEEE Internet of Things Journal, 7(10): 9600–9610.
Geyer R, Klein T, Nabi M, et al., 2017, Differentially Private Federated Learning: A Client Level Perspective, arXiv, https://doi.org/10.48550/arXiv.1712.07557
Guan G, Tao Z, Zhi T, et al., 2024, Privacy Protection Methods for Decentralized Federated Learning in Healthcare Settings. Computer Applications, 44(S2): 112–117.
Niu S, Wang N, Zhou X, et al., 2024, A Secure Federated Learning Scheme for Smart Healthcare Based on Secret Sharing and Homomorphic Encryption. Computer Engineering, 12(8): 1–13.
Wang B, Li H, Wang J, et al., 2023, Privacy-Preserving Federated Learning Architecture for Medical Data. Journal of Xi’an University of Electronic Science and Technology, 50(5): 166–177.
Wen Y, Chen M, 2022, A Medical Data Sharing Solution that Integrates Federated Learning with Blockchain. Computer Engineering, 48(5): 145–153.
