Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Tianshi, Lu, Wen-jie, Yu, Jiangrui, Yi, Chen, Lin, Chenqi, Wang, Runsheng, Li, Meng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911131707113472
author Xu, Tianshi
Lu, Wen-jie
Yu, Jiangrui
Yi, Chen
Lin, Chenqi
Wang, Runsheng
Li, Meng
author_facet Xu, Tianshi
Lu, Wen-jie
Yu, Jiangrui
Yi, Chen
Lin, Chenqi
Wang, Runsheng
Li, Meng
contents This paper presents an efficient framework for private Transformer inference that combines Homomorphic Encryption (HE) and Secure Multi-party Computation (MPC) to protect data privacy. Existing methods often leverage HE for linear layers (e.g., matrix multiplications) and MPC for non-linear layers (e.g., Softmax activation functions), but the conversion between HE and MPC introduces significant communication costs. The proposed framework, dubbed BLB, overcomes this by breaking down layers into fine-grained operators and further fusing adjacent linear operators, reducing the need for HE/MPC conversions. To manage the increased ciphertext bit width from the fused linear operators, BLB proposes the first secure conversion protocol between CKKS and MPC and enables CKKS-based computation of the fused operators. Additionally, BLB proposes an efficient matrix multiplication protocol for fused computation in Transformers. Extensive evaluations on BERT-base, BERT-large, and GPT2-base show that BLB achieves a $21\times$ reduction in communication overhead compared to BOLT (S\&P'24) and a $2\times$ reduction compared to Bumblebee (NDSS'25), along with latency reductions of $13\times$ and $1.8\times$, respectively, when leveraging GPU acceleration.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC
Xu, Tianshi
Lu, Wen-jie
Yu, Jiangrui
Yi, Chen
Lin, Chenqi
Wang, Runsheng
Li, Meng
Cryptography and Security
This paper presents an efficient framework for private Transformer inference that combines Homomorphic Encryption (HE) and Secure Multi-party Computation (MPC) to protect data privacy. Existing methods often leverage HE for linear layers (e.g., matrix multiplications) and MPC for non-linear layers (e.g., Softmax activation functions), but the conversion between HE and MPC introduces significant communication costs. The proposed framework, dubbed BLB, overcomes this by breaking down layers into fine-grained operators and further fusing adjacent linear operators, reducing the need for HE/MPC conversions. To manage the increased ciphertext bit width from the fused linear operators, BLB proposes the first secure conversion protocol between CKKS and MPC and enables CKKS-based computation of the fused operators. Additionally, BLB proposes an efficient matrix multiplication protocol for fused computation in Transformers. Extensive evaluations on BERT-base, BERT-large, and GPT2-base show that BLB achieves a $21\times$ reduction in communication overhead compared to BOLT (S\&P'24) and a $2\times$ reduction compared to Bumblebee (NDSS'25), along with latency reductions of $13\times$ and $1.8\times$, respectively, when leveraging GPU acceleration.
title Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPC
topic Cryptography and Security
url https://arxiv.org/abs/2508.19525