MK-FLFHNN: A Privacy-Preserving Vertical Federated Learning Framework For Heterogeneous Neural Network Via Multi-Key Homomorphic Encryption
Han Sun, Yan Zhang, Zhen Xu, Runmei Zhang, Mingxuan Li · 2023
The security and privacy of Vertical federated learning (VFL) deserve attention due to the computationally strong dependency between participants, which requires frequent and direct interactions. The existing Privacy-preserving (PP) VFL schemes are often limited by the model types supported, the communication cost and the number of participants. To alleviate this issue, we propose MK-FLFHNN, a novel PP framework for heterogeneous neural networks based on xMK-CKKS multi-key homomorphic encryption. The algorithm eliminates the limitation of traditional algorithms limited to generalized linear models and prevents the privacy leakage of shared information while solving the problem of potential leakage from the aggregated values of federated learning, adapting according to the number of participants and supporting flexible expansion to multi-party scenarios. Most importantly, for three-party and above scenarios, the framework is robust to collusion between K