Privacy-Preserving Federated Learning from Partial Decryption Verifiable Threshold Multi-Client Functional Encryption

TL;DR

This paper introduces VTSAFL, a verifiable threshold security protocol for federated learning that enhances privacy, verifiability, and efficiency, especially suitable for resource-constrained IoT devices.

Contribution

It develops a novel partial decryption verifiable threshold multi-client function encryption scheme and applies it to federated learning for secure, verifiable aggregation.

Findings

Achieves same accuracy as existing schemes on MNIST

Reduces training time by over 40%

Decreases communication overhead by up to 50%

Abstract

In federated learning, multiple parties can cooperate to train the model without directly exchanging their own private data, but the gradient leakage problem still threatens the privacy security and model integrity. Although the existing scheme uses threshold cryptography to mitigate the inference attack, it can not guarantee the verifiability of the aggregation results, making the system vulnerable to the threat of poisoning attack. We construct a partial decryption verifiable threshold multi client function encryption scheme, and apply it to Federated learning to implement the federated learning verifiable threshold security aggregation protocol (VTSAFL). VTSAFL empowers clients to verify aggregation results, concurrently minimizing both computational and communication overhead. The size of the functional key and partial decryption results of the scheme are constant, which provides efficiency guarantee for large-scale deployment. The experimental results on MNIST dataset show that vtsafl can achieve the same accuracy as the existing scheme, while reducing the total training time by more than 40%, and reducing the communication overhead by up to 50%. This efficiency is critical for overcoming the resource constraints inherent in Internet of Things (IoT) devices.