Editorial
A Communication-Reduced Privacy-Preserving ViT Inference Framework for Distributed Edge Intelligence
@ARTICLE{10.4108/eetsis.13362, author={Tingting Chen}, title={A Communication-Reduced Privacy-Preserving ViT Inference Framework for Distributed Edge Intelligence}, journal={EAI Endorsed Transactions on Scalable Information Systems}, volume={13}, number={2}, publisher={EAI}, journal_a={SIS}, year={2026}, month={8}, keywords={privacy-preserving inference, secret sharing, Vision Transformer, fixed-point arithmetic, distributed edge intelligence, communication reduction}, doi={10.4108/eetsis.13362} }- Tingting Chen
Year: 2026
A Communication-Reduced Privacy-Preserving ViT Inference Framework for Distributed Edge Intelligence
SIS
EAI
DOI: 10.4108/eetsis.13362
Abstract
To address privacy leakage from user images, intermediate representations, and outputs during Vision Transformer (ViT) inference in distributed edge services, this paper presents SViT, a two-server secret-sharing framework with offline correlated randomness. The revised design specifies fixed-point arithmetic over the ring Z_(2^64) with 16 fractional bits, fresh one-time masks, probabilistic truncation, numerical ranges, and complete input-output procedures for SExp, SDiv, SSqrt, SVar, SLayerNorm, SSoftmax, and SGeLU. The protocols use fixed-depth range reduction, lookup-assisted initialization, and a constant number of Newton updates, so their online depth is independent of numerical convergence tolerances. Under the semi-honest, non-colluding-server model, the revised security analysis defines approximate ideal functionalities, public leakage, simulator inputs, and sequential composition. Existing microbenchmarks show 2.28-6.50 times lower runtime and 4.00-14.20 times lower online communication than CrypTen for the reported core operators; for SDiv, runtime decreases from 9.1 ms to 1.4 ms and communication from 10.8337 MB to 0.7629 MB. Synthetic Q16 numerical checks report maximum absolute errors of 5.10×10−5 for SExp and 4.73×10−4 for SGeLU, maximum relative errors of 1.27×10−5 for reciprocal and 3.72×10−5 for square root, and 100% top-1 consistency over 10,000 randomly generated Softmax vectors. The reported end-to-end result remains 3799.744 ms and 2.85 GB per inference; therefore, SViT is described as communication-reduced relative to the evaluated MPC baselines rather than universally lightweight, and its present practical scope is primarily high-bandwidth LAN or provider-edge deployments.
Copyright © 2026 Tingting Chen, licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
