PackVFL: Efficient HE Packing for Vertical Federated Learning

arXiv:2405.00482v1 Announce Type: cross
Abstract: As an essential tool of secure distributed machine learning, vertical federated learning (VFL) based on homomorphic encryption (HE) suffers from severe efficiency problems due to data inflation and time-consuming operations. To this core, we propose PackVFL, an efficient VFL framework based on packed HE (PackedHE), to accelerate the existing HE-based VFL algorithms. PackVFL packs multiple cleartexts into one ciphertext and supports single-instruction-multiple-data (SIMD)-style parallelism. We focus on designing a high-performant matrix multiplication (MatMult) method since …

abstract arxiv core cs.cr cs.lg data distributed efficiency encryption federated learning framework homomorphic encryption inflation machine machine learning operations tool type