Progressive-Resolution Secure Aggregation for Federated Learning

2026-09-30

AI Summary

This study addresses the limitation of fixed precision in traditional secure aggregation protocols by introducing a progressive-resolution secure aggregation paradigm. Methodologically, it proposes a nested-lattice-compatible clipping-and-dithering update mechanism, combined with an additional padding layer secured through non-colluding controllers, to decouple aggregation precision from client interaction rounds. This framework enables clients to obtain multi-stage, variable-resolution aggregated results on demand following a single upload. By progressively enhancing precision without requiring repeated participation, the proposed approach significantly reduces communication overhead while preserving strong security guarantees.

Abstract

Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the aggregate precision when clients upload. We introduce and formulate a new progressive-resolution secure-aggregation functionality in which clients upload once and successively finer resolutions of the same aggregate can later be authorized without renewed client participation. To realize this functionality, we propose progressive-resolution secure aggregation (PSA): each clipped, dithered update is represented by compatible nested-lattice digits; separately releasable layers are protected by secure aggregation and an additional aggregate pad that remains unavailable to the server until a non-colluding release controller authorizes that layer.

Problem

• Federated Learning
• Secure Aggregation
• Progressive Resolution
• Privacy-preserving

Innovation

• Federated Learning
• Secure Aggregation
• Progressive-Resolution
• Nested Lattices
• Release Controller