Security and Privacy

Federated learning allows data to be locally trained in their device and only send model updates to the central server for aggregation. But the security of model updates in the aggregation should also be carefully addressed. Existing works mainly focus on secure multiparty computation or differential privacy, which depends on heavy encryption or brings low accuracy. In this chapter, we discuss an efficient secure aggregation method for model updates in federated learning by pre-processing the model updates from each participant and only encrypting portion of the processed updates by functional encryption for inner product to protect the whole parameters, thus achieving efficient aggregation of model update vectors.