Practical Multi-Key Homomorphic Encryption for More Flexible and Efficient Secure Federated Average Aggregation

In this work, we introduce a lightweight communication-efficient multi-key approach suitable for the Federated Averaging rule. By combining secret-key RLWE-based HE, additive secret sharing and PRFs, we reduce approximately by a half the communication cost per party when compared to the usual public...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Cyber Security and Resilience (CSR) pp. 612 - 617
Main Authors Pedrouzo-Ulloa, Alberto, Boudguiga, Aymen, Chakraborty, Olive, Sirdey, Renaud, Stan, Oana, Zuber, Martin
Format Conference Proceeding
LanguageEnglish
Published IEEE 31.07.2023
Subjects
Additives
Computer crime
Costs
Federated Learning
Homomorphic encryption
Lattices
Multi-Key Encryption
Public key
Resilience
Secret-Key Encryption
Secure Federated Average Aggregation
Online AccessGet full text
DOI10.1109/CSR57506.2023.10224979

Cover

More Information
Summary:In this work, we introduce a lightweight communication-efficient multi-key approach suitable for the Federated Averaging rule. By combining secret-key RLWE-based HE, additive secret sharing and PRFs, we reduce approximately by a half the communication cost per party when compared to the usual public-key instantiations, while keeping practical homomorphic aggregation performances. Additionally, for LWE-based instantiations, our approach reduces the communication cost per party from quadratic to linear in terms of the lattice dimension.
DOI:10.1109/CSR57506.2023.10224979