BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers

ePrint Report: BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers

Qi Pang, Jinhao Zhu, Helen Möllering, Wenting Zheng, Thomas Schneider

The advent of transformers has brought about significant advancements in traditional machine learning tasks. However, their pervasive deployment has raised concerns about the potential leakage of sensitive information during inference. Existing approaches using secure multiparty computation (MPC) face limitations when applied to transformers due to the extensive model size and resource-intensive matrix-matrix multiplications. In this paper, we present BOLT, a …

deployment eprint report information machine machine learning privacy report schneider sensitive sensitive information thomas transformers