Secure and privacy preserved homomorphically encrypted healthcare data analysis in edge cloud paradigm based on federated learning strategies
Abstract
This research proposes a privacy-preserving federated learning framework for healthcare data using homomorphic encryption, featuring the novel Homomorphic Encryption-based Adaptive Tuning for Federated Learning (HEAT-FL) approach. HEAT-FL dynamically adjusts encryption parameters based on model layer sensitivity to balance security, computational overhead, and model accuracy. Additionally, encrypted inference and hybrid homomorphic encryption (HHE) mechanisms are explored, demonstrating secure model deployment while preserving patient data confidentiality.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.