Federated Learning Privacy-Preserving Approach for Consumer-Centric Multimodal Healthcare Data
- 26 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. PP (00983063) , 1
Abstract
Electronic Health Records (EHR) data have become a valuable resource for biomedical research. By leveraging federated learning (FL), the potential of EHR data can be used without compromising privacy. However, most existing studies focus on privacy protection methods for device-centric distributed healthcare EHRs. The diverse modalities of EHR, such as consumer-centric clinical notes, lab results, and imaging data, limit the unimodal ability to capture complex relationships. FL models designed for unimodal data struggle to integrate these heterogeneous sources, resulting in suboptimal performance and increased risk of privacy breaches. This paper proposes a FL privacy protection method for multimodal data to address these limitations. The proposed method effectively handles diverse data types while ensuring robust privacy protection across the entire FL lifecycle. To prevent adversaries from stealing original data through reverse attacks, differential privacy perturbation is applied to the model parameters uploaded by each participant. Additionally, the Paillier cryptosystem is utilized for homomorphic encryption of local model parameters to protect local model information during training. Experimental results demonstrate that the proposed method provides comprehensive privacy protection for training data and models with minimal performance loss, making it suitable for federated learning scenarios involving multimodal EHR data.Keywords
Funding Information
- Indian Institute of Information Technology (IIIT) Bhopal, India, under institutional research support
This publication has 34 references indexed in Scilit:
- HierFedPDP:Hierarchical federated learning with personalized differential privacyJournal of Information Security and Applications, 2024
- Contract-based hierarchical security aggregation scheme for enhancing privacy in federated learningJournal of Information Security and Applications, 2024
- Privacy-preserving blockchain-based federated learning for brain tumor segmentationComputers in Biology and Medicine, 2024
- A federated learning system with data fusion for healthcare using multi-party computation and additive secret sharingComputer Communications, 2024
- Encrypted federated learning for secure decentralized collaboration in cancer image analysisMedical Image Analysis, 2023
- Minimum Gaussian Noise Variance of Federated Learning in the Presence of Mutual Information Based Differential PrivacyIEEE Access, 2023
- Poisoning Attacks in Federated Learning: A SurveyIEEE Access, 2023
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- PPT: A privacy-preserving global model training protocol for federated learning in P2P networksComputers & Security, 2022
- Privacy protection federated learning system based on blockchain and edge computing in mobile crowdsourcingComputer Networks, 2022