Work

Accelerating Private Large Transformers Inference Through Fine-Grained Collaborative Computation

Year: 2025

Type: article

Abstract: Homomorphic encryption (HE) and secret sharing (SS) enable computations on encrypted data, providing significant privacy benefits for large transformer-based models (TBM) in sensitive sectors like medicine and finance. However, private TBM inference incurs significant costs due to the coarse-grained application of HE and SS. We present FASTLMPI, a new approach to accelerate private TBM inference through fine-grained computation optimization. Specifically, through the fine-grained co-design of homomorphic encryption and secret sharing, FASTLMPI achieves efficient protocols for matrix multiplication, SoftMax, LayerNorm, and GeLU. In addition, FASTLMPI introduces a precise segmented approximation technique for differentiable non-linear functions, improving its fitting accuracy while maintaining a low polynomial degree. Compared to solution BOLT (S&P’24), FASTLMPI shows a remarkable 25.1% to 55.3% decrease in runtime and an impressive 39.0% reduction in communication costs.

Source: IEEE Transactions on Information Forensics and Security

DOI: 10.1109/tifs.2025.3584639

Authors: Yuntian Chen, Zhanyong Tang, Tianpei Lu, Bingsheng Zhang, Zhiying Shi, Zheng Wang

Institutions: Northwest University, Zhejiang University, University of Leeds

Language: English

Topic: Cryptography and Data Security

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

Award: G1589916337