SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference

Published by

eprint.iacr.org

on •1 min read

SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference

A growing adoption of transformer-based machine learning models is raising concerns about sensitive data exposure. Nonetheless, current secure inference solutions incur substantial overhead due to their extensive reliance on non-linear protocols, such as softmax and Gaussian error linear unit...

Secure multiparty computation Softmax Model privacy Constant-round Transformer Inference Privacy-preserving ML GELU ONNX Cryptographic protocols

Learn more