Non-Interactive, Secure Verifiable Aggregation for Decentralized, Privacy-Preserving Learning
Published in In *Australasian Conference on Information Security and Privacy* (ACISP), 2021
We propose a non-interactive and secure verifiable aggregation protocol for decentralized, privacy-preserving learning. The scheme allows efficient aggregation of model updates without compromising user privacy and without requiring interaction during verification.
Recommended citation: Carlo Brunetta, Georgia Tsaloli, Bei Liang, Gustavo Banegas, Aikaterini Mitrokotsa. (2021). "Non-Interactive, Secure Verifiable Aggregation for Decentralized, Privacy-Preserving Learning." In Australasian Conference on Information Security and Privacy (ACISP).
Download Paper | Download Slides | Download Bibtex