Document Type
Article
Publication Date
2025
DOI
10.1007/s44163-025-00630-0
Publication Title
Discover Artificial Intelligence
Volume
5
Issue
1
Pages
392 (1-21)
Abstract
This study examines neural cryptography with homomorphic operations as an alternative secure aggregation method for federated learning (FL). It proposes a novel neural cryptographic system supporting homomorphic addition on fixed-point encrypted data, and consisting of three networks, namely (1) an encryption network (Alice), (2) a homomorphic network (HO), and (3) a decryption network (Bob), along with an adversarial Eve network. Using the MNIST dataset, the proposed Neural Homomorphic Operation System (NHOS) is evaluated against a plaintext baseline and the CKKS scheme, a widely used public-key homomorphic encryption method. The results show that the proposed NHOS approach offers a satisfying performance, i.e., 88.10% accuracy, using quantized weights, highlighting its potential as a lightweight alternative to traditional homomorphic encryption in FL.
Rights
© The Authors 2025.
This article is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original authors and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Data Availability
Article states: "No datasets were generated or analysed during the current study."
Original Publication Citation
Sele, E., Catak, F. O., Seo, J., & Kuzlu, M. (2025). Secure federated learning via neural cryptography with homomorphic operations. Discover Artificial Intelligence, 5(1), 1-21, Article 392. https://doi.org/10.1007/s44163-025-00630-0
ORCID
0000-0002-8719-2353 (Kuzlu)
Repository Citation
Sele, Espen; Catak, Ferhat Ozgur; Seo, Jungwon; and Kuzlu, Murat, "Secure Federated Learning Via Neural Cryptography with Homomorphic Operations" (2025). Engineering Technology Faculty Publications. 270.
https://digitalcommons.odu.edu/engtech_fac_pubs/270