Researchers have developed a novel four-phase protocol for privacy-enhanced federated learning (FL) that utilizes the xMK-CKKS multi-key homomorphic encryption scheme over wireless channels. This protocol enables secure aggregation of encrypted data without requiring channel estimation, addressing vulnerabilities in single-key HE methods. The proposed system integrates with zero-order FL, ensuring security against a server colluding with up to N-1 clients and maintaining an O(1/sqrt(K)) convergence rate, as validated by numerical results on MNIST. AI
IMPACT This research could lead to more secure and private federated learning systems, crucial for sensitive data applications.
RANK_REASON The cluster contains a research paper detailing a new protocol for federated learning.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →