Abstract
Online Medical Pre-Diagnosis (OMPD) systems based on machine learning will benefit individuals for automatic diagnosis while saving time and costs. The inherent security constraints and distributed setting of patient data form obstacles in constructing reliable OMPD models. Existing privacy-preserving machine learning approaches incur substantial communication and computation cost, and are susceptible to inference attacks. Moreover, to accommodate cryptography primitives, machine learning schemes in the encrypted domain are substituted by approximation models, leading to accuracy loss. To mitigate these problems, we build PriD , an efficient and accurate model for achieving an OMPD system. PriD solution i) guarantees confidentiality against inference attacks by defensive mechanism; ii) does not require interaction between users and server by mask matrix; iii) without any approximation by functional encryption. The experimental evaluations illustrate that our PriD scheme can reduce the computation overhead substantially compared with the advanced methods while achieving high precision.
Funding Information
  • National Natural Science Foundation of China (12361079, 12201149)
  • Natural Science Foundation of Guangxi Province (2023GXNSFAA026067)
  • GUET (2024YCXS112)

This publication has 23 references indexed in Scilit: