Welcome to the resource topic for 2023/1763
Title:
Secure Transformer Inference
Authors: Mu Yuan, Lan Zhang, Xiang-Yang Li
Abstract: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.
ePrint: https://eprint.iacr.org/2023/1763
See all topics related to this paper.
Feel free to post resources that are related to this paper below.
Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.
For more information, see the rules for Resource Topics .