A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption
By: Khoa Nguyen, Tanveer Khan, Antonis Michalas
Potential Business Impact:
Lets computers learn together safely, without sharing secrets.
Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising approach for privacy-sensitive domains. Despite its potential, FL faces significant challenges, particularly in terms of communication overhead and data privacy. Privacy-preserving Techniques (PPTs) such as Homomorphic Encryption (HE) have been used to mitigate these concerns. However, these techniques introduce substantial computational and communication costs, limiting their practical deployment. In this work, we explore how Hybrid Homomorphic Encryption (HHE), a cryptographic protocol that combines symmetric encryption with HE, can be effectively integrated with FL to address both communication and privacy challenges, paving the way for scalable and secure decentralized learning system.
Similar Papers
Federated Learning: An approach with Hybrid Homomorphic Encryption
Cryptography and Security
Keeps private data safe while training AI.
A Privacy-Preserving Federated Learning Method with Homomorphic Encryption in Omics Data
Cryptography and Security
Keeps medical secrets safe, still finds cures.
Emerging Paradigms for Securing Federated Learning Systems
Cryptography and Security
Makes AI learn from data without seeing it.