Ditto: Quantization-aware Secure Inference of Transformers upon MPC

no code implementations • 9 May 2024 • Haoqi Wu, Wenjing Fang, Yancheng Zheng, Junming Ma, Jin Tan, Yinggui Wang, Lei Wang

Then, we propose novel MPC primitives to support the type conversions that are essential in quantization and implement the quantization-aware MPC execution of secure quantized inference.

Quantization

SpotTune: Leveraging Transient Resources for Cost-efficient Hyper-parameter Tuning in the Public Cloud

no code implementations • 7 Dec 2020 • Yan Li, Bo An, Junming Ma, Donggang Cao, Yasha Wang, Hong Mei

Hyper-parameter tuning (HPT) is crucial for many machine learning (ML) algorithms.

BIG-bench Machine Learning

S3ML: A Secure Serving System for Machine Learning Inference

no code implementations • 13 Oct 2020 • Junming Ma, Chaofan Yu, Aihui Zhou, Bingzhe Wu, Xibin Wu, Xingyu Chen, Xiangqun Chen, Lei Wang, Donggang Cao

We present S3ML, a secure serving system for machine learning inference in this paper.

BIG-bench Machine Learning Management +1