Paper 2026/2497
SecAgg++: A Post-Quantum Privacy Preserving Federated Learning Protocol
Abstract
Secure aggregation is a fundamental building block for privacy-preserving federated learning, yet most existing masking-based secure aggregation protocols do not provide post-quantum security. In this work, we present SecAgg++, a masking-based post-quantum secure aggregation protocol for the single-server setting. SecAgg++ integrates post-quantum cryptographic primitives while preserving the communication and computational efficiency of classical frameworks such as SecAgg and SecAgg+, and supports client dropout handling through an efficient recovery procedure.
Metadata
- Available format(s)
-
PDF
- Category
- Applications
- Publication info
- Published elsewhere. AISec: 19 th ACM Workshop on Artificial Intelligence and Security
- DOI
- 10.1145/3847352.3848087
- Keywords
- Secure AggregationPost-Quantum CryptographyFederated LearningSecret SharingAdditive Masking
- Contact author(s)
-
aperez @ fbk eu
gcavicchioni @ fbk eu
scretti @ fbk eu
rlongo @ fbk eu
altomasi @ fbk eu
ranise @ fbk eu - History
- 2026-10-15: approved
- 2026-10-15: received
- See all versions
- Short URL
- https://ia.cr/2026/2497
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2026/2497,
author = {Alessandro Perez and Giulia Cavicchioni and Silvio Cretti and Riccardo Longo and Alessandro Tomasi and Silvio Ranise},
title = {{SecAgg}++: A Post-Quantum Privacy Preserving Federated Learning Protocol},
howpublished = {Cryptology {ePrint} Archive, Paper 2026/2497},
year = {2026},
doi = {10.1145/3847352.3848087},
url = {https://eprint.iacr.org/2026/2497}
}