Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks
This work solves privacy and efficiency problems in federated learning for clients needing secure collaborative training, but it is incremental as it builds on existing encryption and neural network techniques.
The paper tackled privacy-preserving federated learning by developing Homomorphic Adversarial Networks (HANs) to address accuracy degradation and key-sharing issues, resulting in negligible accuracy loss (at most 1.35%) and a 6,075 times speedup in encryption aggregation compared to traditional methods.
Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable degradation in accuracy, the requirement for sharing keys, and cooperation during the key generation or decryption processes. As a mitigation, we develop the first protocol that utilizes neural networks to implement PPFL, as well as incorporating an Aggregatable Hybrid Encryption scheme tailored to the needs of PPFL. We name these networks as Homomorphic Adversarial Networks (HANs) which demonstrate that neural networks are capable of performing tasks similar to multi-key homomorphic encryption (MK-HE) while solving the problems of key distribution and collaborative decryption. Our experiments show that HANs are robust against privacy attacks. Compared with non-private federated learning, experiments conducted on multiple datasets demonstrate that HANs exhibit a negligible accuracy loss (at most 1.35%). Compared to traditional MK-HE schemes, HANs increase encryption aggregation speed by 6,075 times while incurring a 29.2 times increase in communication overhead.