Paper 2023/1269
SIGMA: Secure GPT Inference with Function Secret Sharing
Abstract
Secure 2-party computation (2PC) enables secure inference that offers protection for both proprietary machine learning (ML) models and sensitive inputs to them. However, the existing secure inference solutions suffer from high latency and communication overheads, particularly for transformers. Function secret sharing (FSS) is a recent paradigm for obtaining efficient 2PC protocols with a preprocessing phase. We provide SIGMA, the first end-to-end system for secure transformer inference based on FSS. By constructing new FSS-based protocols for complex machine learning functionalities, such as Softmax, GeLU and SiLU, and also accelerating their computation on GPUs, SIGMA improves the latency of secure inference of transformers by $11-19\times$ over the state-of-the-art that uses preprocessing and GPUs. We present the first secure inference of generative pre-trained transformer (GPT) models. In particular, SIGMA executes Meta's LLaMA2 (available on HuggingFace) with 13 billion parameters in 44 seconds and GPT2 in 1.6 seconds.
Metadata
- Available format(s)
-
PDF
- Category
- Cryptographic protocols
- Publication info
- Published elsewhere. Minor revision. 24th Privacy Enhancing Technologies Symposium (PETS 2024)
- Keywords
- Function Secret SharingMPCSecure inferencetransformersGPT
- Contact author(s)
-
kanav0610 @ gmail com
jawalkarp @ iisc ac in
t-mukherjeea @ microsoft com
nichandr @ microsoft com
divya gupta @ microsoft com
ashishpanwar @ microsoft com
rahsha @ microsoft com - History
- 2024-07-15: last of 2 revisions
- 2023-08-22: received
- See all versions
- Short URL
- https://ia.cr/2023/1269
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2023/1269,
author = {Kanav Gupta and Neha Jawalkar and Ananta Mukherjee and Nishanth Chandran and Divya Gupta and Ashish Panwar and Rahul Sharma},
title = {{SIGMA}: Secure {GPT} Inference with Function Secret Sharing},
howpublished = {Cryptology {ePrint} Archive, Paper 2023/1269},
year = {2023},
url = {https://eprint.iacr.org/2023/1269}
}
