ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
This addresses the practical implementation challenges in federated learning for practitioners by providing a tunable system, though it is incremental as it builds on existing methods like differential privacy and homomorphic encryption.
The paper tackles the rigid trade-off between model utility and computational efficiency in federated learning protection mechanisms by introducing ParaAegis, a parallel protection framework that allows flexible control over privacy-utility-efficiency balance, with experimental results showing adjustable prioritization between accuracy and training time.
Federated learning (FL) faces a critical dilemma: existing protection mechanisms like differential privacy (DP) and homomorphic encryption (HE) enforce a rigid trade-off, forcing a choice between model utility and computational efficiency. This lack of flexibility hinders the practical implementation. To address this, we introduce ParaAegis, a parallel protection framework designed to give practitioners flexible control over the privacy-utility-efficiency balance. Our core innovation is a strategic model partitioning scheme. By applying lightweight DP to the less critical, low norm portion of the model while protecting the remainder with HE, we create a tunable system. A distributed voting mechanism ensures consensus on this partitioning. Theoretical analysis confirms the adjustments between efficiency and utility with the same privacy. Crucially, the experimental results demonstrate that by adjusting the hyperparameters, our method enables flexible prioritization between model accuracy and training time.