FLUE: Federated Learning with Un-Encrypted model weights
This addresses privacy concerns for users in federated learning systems by proposing an encryption-free method, though it appears incremental as it builds on existing coded gradient approaches.
The paper tackles the privacy vulnerability in federated learning where gradients can be reverse-engineered to expose private data, even with noise, by introducing a novel algorithm that uses coded local gradients without encryption, injecting surplus noise for enhanced privacy, and demonstrating convergence and promising simulation results.
Federated Learning enables diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Despite existing privacy measures, concerns arise from potential reverse engineering of gradients, even with added noise, revealing private data. To address this, recent research emphasizes using encrypted model parameters during training. This paper introduces a novel federated learning algorithm, leveraging coded local gradients without encryption, exchanging coded proxies for model parameters, and injecting surplus noise for enhanced privacy. Two algorithm variants are presented, showcasing convergence and learning rates adaptable to coding schemes and raw data characteristics. Two encryption-free implementations with fixed and random coding matrices are provided, demonstrating promising simulation results from both federated optimization and machine learning perspectives.