Secure Transformer Inference

ePrint Report: Secure Transformer Inference

Mu Yuan, Lan Zhang, Xiang-Yang Li

We present a three-party protocol that can protect both Transformer parameters and user data during the inference phase. For each feedforward inference process, our protocol only introduces permutation computation of input and output data on the user side. Our protocol, Secure Transformer Inference Protocol (STIP), can be applied to real-world services like ChatGPT.

computation data eprint report input lan party process protect protocol report user data