Communication-Computation Efficient Secure Aggregation for Federated Learning
This work provides a more efficient method for securing federated learning, which is critical for organizations and individuals concerned about data privacy during distributed model training.
This paper addresses the high communication and computation costs of secure aggregation in federated learning by proposing a new scheme. By using a sparse random graph for secret-sharing nodes, their method achieves similar reliability and data privacy while using only 20-30% of the resources compared to existing secure solutions.
Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data contents off model parameters transmitted during federated learning. A recent solution based on the secure aggregation primitive enabled privacy-preserving federated learning, but at the expense of significant extra communication/computational resources. In this paper, we propose a low-complexity scheme that provides data privacy using substantially reduced communication/computational resources relative to the existing secure solution. The key idea behind the suggested scheme is to design the topology of secret-sharing nodes as a sparse random graph instead of the complete graph corresponding to the existing solution. We first obtain the necessary and sufficient condition on the graph to guarantee both reliability and privacy. We then suggest using the Erdős-Rényi graph in particular and provide theoretical guarantees on the reliability/privacy of the proposed scheme. Through extensive real-world experiments, we demonstrate that our scheme, using only $20 \sim 30\%$ of the resources required in the conventional scheme, maintains virtually the same levels of reliability and data privacy in practical federated learning systems.