通信学报2024，Vol.45Issue(4)：27-38,12.DOI:10.11959/j.issn.1000-436x.2024025
基于秘密共享的轻量级隐私保护ViT推理框架
Light weighted privacy protection ViT inference framework based on secret sharing
摘要
Abstract
The ViT(vision transformer)inference framework,which was widely used in image processing,was found to have a risk of leaking user privacy data.However,existing privacy protection inference frameworks had problems such as low computational efficiency and high online communication volume.To address this issue,a highly efficient privacy protection inference framework SViT was proposed.Two edge servers collaborated to execute secure computing proto-cols based on secret sharing design,such as SSoftmax,SLayerNorm,SGeLU,etc.While maintaining the original frame-work structure of ViT-B/16,the problem of large inference overhead in privacy protection framework was solved.Theo-retical analysis and experiments show that compared to Crypton,SViT has improved computational efficiency by 2～6 times and online communication overhead by 4～14 times,respectively.关键词
隐私保护/秘密共享/图像分类/安全计算协议Key words
privacy protection/secret sharing/image classification/secure computing protocol分类
信息技术与安全科学引用本文复制引用
马敏,付钰,黄凯,贾潇风..基于秘密共享的轻量级隐私保护ViT推理框架[J].通信学报,2024,45(4):27-38,12.基金项目
国家自然科学基金资助项目(No.62102422)The National Natural Science Foundation of China(No.62102422) （No.62102422）
