Hybrid encryption protects federated updates in Medical-MNIST test

A hybrid Paillier-CKKS encryption framework achieved 94.67% average accuracy on the Medical-MNIST dataset while clients transmitted encrypted model updates during simulated reverse-engineering attacks. The experiment also produced an average structural similarity index measure, or SSIM, of 0.055, according to a study in Neural Computing and Applications . The authors reported that the system defended against model inversion while balancing privacy and computational efficiency, although the evaluation was limited to one dataset and simulated attacks.

The study addresses two privacy risks associated with collaborative modeling across institutions: sharing raw data and exchanging model parameters that may leak information about the underlying records. At the technical core is the combination of two homomorphic encryption schemes. Paillier supports integer homomorphic operations and was used to protect vulnerable gradient components.

The Cheon-Kim-Kim-Song scheme, commonly called CKKS, supports batch encoding and approximate homomorphic processing of high-dimensional, non-sensitive gradients. The researchers said this division of labor was intended to reduce communication and computation costs while assigning stronger protection to the more vulnerable parts of an update. Additive homomorphism allows encrypted gradient contributions to be accumulated in coded form, enabling global model updates without exposing the participating clients’ encrypted codes through a decryption step.

Beyond encryption, the proposed framework includes an anomaly-detection method and a fine-grained access-control technique combining role-based and attribute-based access control. The anomaly-detection component is designed to eliminate abnormal gradients, while the access-control mechanism limits unauthorized operations. These features operate alongside the two encryption schemes within the federated-learning infrastructure, adding checks on model traffic and controls over permitted actions rather than relying on encryption alone.

The available evidence describes a computational evaluation rather than a clinical deployment or a study involving human participants. Testing centered on the Medical-MNIST dataset and simulated reverse-engineering attacks, with average accuracy of 94.67% and average SSIM of 0.055. The results support the reported defense against model inversion under the tested conditions, but the supplied study summary does not establish performance on other datasets, in live hospital networks, under real-world attacks or across different numbers of participating institutions.

The research is therefore a dataset-specific demonstration of encrypted federated aggregation, access controls and anomaly detection, rather than evidence that the framework eliminates privacy risks in collaborative machine learning.

Subject of Research: Evaluation of hybrid homomorphic encryption for privacy-preserving federated learning on Medical-MNIST

Article Title: Privacy protection of multi-source data combined with homomorphic encryption within a federated learning framework

Article References: Wang, S., & Jia, X. (2026). Privacy protection of multi-source data combined with homomorphic encryption within a federated learning framework. Neural Computing and Applications, 38(20), Article 822. https://doi.org/10.1007/s00521-026-12594-y

Image Credits: AI Generated

DOI: 10.1007/s00521-026-12594-y

Keywords: federated learning, homomorphic encryption, Paillier encryption, CKKS encryption, Medical-MNIST, encrypted model updates, model inversion, anomaly detection, access control, privacy-preserving AI, Privacy, protection