Paper 2026/491
SoK: Private Transformer-Based Model Inference
, Northwest University, Zhejiang University, Northwest University, Zhejiang University, Northwest UniversityAbstract
The growing demand for privacy-preserving Transformer inference has led to the emergence of numerous protocols designed to protect sensitive data and model parameters. These protocols utilize diverse cryptographic tools under varying assumptions, each presenting unique characteristics and trade-offs between computation, communication, and accuracy. In this paper, we conduct a systematic and in-depth analysis of existing approaches from diverse performance perspectives, identifying their limitations and research gaps. We further evaluate the reproducibility of prior systems and re-benchmark representative solutions under standardized configurations. Our results yield a principled guideline for balancing protocol trade-offs under different deployment settings.
Note: Update intro and Table in appendix
Metadata
- Available format(s)
-
PDF
- Category
- Applications
- Publication info
- Published elsewhere. Major revision. USENIX Security
- Keywords
- PPML
- Contact author(s)
-
chenyt_x @ 163 com
lutianpei @ zju edu cn
zytang @ nwu edu cn
bingsheng @ zju edu cn
shizhiying @ stumail nwu edu cn
luanxx @ stumail nwu edu cn
zzwang @ nwu edu cn - History
- 2026-07-20: last of 4 revisions
- 2026-03-09: received
- See all versions
- Short URL
- https://ia.cr/2026/491
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2026/491,
author = {Yuntian Chen and Tianpei Lu and Zhanyong Tang and Bingsheng Zhang and Zhiying Shi and Yuxiang Luan and Zhuzhu Wang},
title = {{SoK}: Private Transformer-Based Model Inference},
howpublished = {Cryptology {ePrint} Archive, Paper 2026/491},
year = {2026},
url = {https://eprint.iacr.org/2026/491}
}
