🤖 AI Summary
This work addresses the high communication overhead and security risks inherent in existing single-server secure aggregation protocols, which rely on the server to relay sensitive data among users. To overcome these limitations, the authors propose a novel two-layer secret sharing protocol that integrates Shamir’s secret sharing with 2-out-of-2 additive secret sharing, enhanced by pseudorandom functions (PRFs) and key-homomorphic PRFs (KhPRFs). This design enables secure aggregation without requiring direct user-to-user communication or server-mediated data forwarding. Furthermore, the protocol introduces an innovative encoding mechanism based on the Chinese Remainder Theorem, substantially reducing computational and communication costs for high-dimensional data. Experimental results demonstrate that, in a setting with 100 users and input length $2^{18}$, the approach reduces communication overhead by nearly 100×, decreases computation time by 51%–75%, and lowers overall computational cost by approximately 17%.
📝 Abstract
Federated Learning (FL) enables collaborative model training while preserving privacy by keeping data local. However, the risk of sensitive data leakage through model updates necessitates the use of secure aggregation protocols. Existing server-based secure aggregation protocols typically require the server to forward sensitive data shared between users, which increases communication overhead and introduces potential security risks. In this work, we propose a novel secure aggregation protocol based on two-layer secret sharing to address these issues. By combining Shamir's Secret Sharing with 2-out-of-2 additive secret sharing using a Pseudo-Random Function (PRF), our protocol eliminates direct communication between users, thereby removing the need for the server to forward data. We further extend the protocol with Key-homomorphic PRF (KhPRF) to support high-dimensional data aggregation and apply it to FL, enabling one-shot secure aggregation with a single server and no intermediary data forwarding. To reduce user overhead, we design a new encoding method based on the Chinese Remainder Theorem for the almost KhPRF-based mask, reducing the number of KhPRF calls and mitigating the model update expansion issue after masking. Experimental results show that our scheme significantly outperforms existing methods in terms of auxiliary node overhead. For instance, when the number of users is 100, our scheme improves communication efficiency by nearly 100 times and reduces computational overhead by approximately 17\%. Moreover, user computation time can be reduced by 51\% to 75\% when the input length is $2^{18}$.