Authors: Yuqi Guo, Lin Li, Zhongxiang Zheng, Hanrui Yun, Ruoyan Zhang, Xiaolin Chang, Zhixuan Gao

Published on: March 18, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2403.11519

Summary

• What is new: Implementation of novel Federated Learning Schemes using the latest homomorphic encryption technologies, aimed at enhancing security, functionality, and practicality.
• Why this is important: Existing Federated Learning schemes lack adequate security, efficiency, and practical application.
• What the research proposes: A set of novel Federated Learning Schemes that utilize the latest homomorphic encryption technologies for improved security, functionality, and practicality.
• Results: Significant improvements in security, efficiency, and practicality on four practical datasets from medical, business, biometric, and financial fields.

Technical Details

Technological frameworks used: Federated Learning

Models used: Homomorphic Encryption technologies

Data used: Medical, business, biometric, and financial datasets

Potential Impact

Healthcare, finance, biometrics, and various business sectors utilizing data sharing and analysis

Want to implement this idea in a business?

We have generated a startup concept here: SecureLearn.