FLRSP: privacy-preserving federated learning using randomly selected model parameters

In this paper, the authors propose a method for privacy-preserving federated learning (FL) that uses randomly selected model parameters to update global models. High-quality deep neural network models require a huge amount of training data in general, but model training raises privacy concerns when dealing with sensitive or personal information. FL is a distributed machine learning framework in which multiple clients and a server train a model collaboratively. However, if the shared updates are compromised, an attacker may reconstruct the original training data. In addition, previous methods for improving robustness generally reduce the accuracy. To overcome these issues, in this method called federated learning using randomly selected model parameters, model parameters computed in each local server are randomly selected and shared to update a global model in a central server. In experiments, image classification tasks were carried out on the ResNet34 architecture and the Vision Transformer under the use of Federated Stochastic Gradient Descent and Federated Averaging, and the results demonstrated the effectiveness of the proposed method in terms of image classification accuracy and robustness against state-of-the-art attacks compared with previous methods.