Method for local differential privacy protection of medical data

The GRR algorithm, which optimizes medical data by classifying its sensitivity and disease relevance, solves the problems of data distortion and insufficient privacy protection in existing technologies, and achieves efficient privacy protection and data utilization.

CN122369758APending Publication Date: 2026-07-10NANJING INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610411427.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-31
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing differential privacy protection methods for localized medical data based on the GRR algorithm suffer from severe distortion after data perturbation and insufficient targeted privacy protection. Furthermore, traditional methods fail to effectively distinguish the differences in sensitivity of diseases.

Method used

A sensitivity grading mechanism is adopted to calculate disease sensitivity scores based on indicators such as the genetic risk index, social discrimination, and average treatment cost of the disease. Privacy budgets are dynamically allocated, and the perturbation probability rules of the GRR algorithm are optimized in combination with disease relevance to implement differentiated data perturbation.

Benefits of technology

It significantly reduces data distortion, improves the targeting and accuracy of privacy protection, ensures the availability and security of data after perturbation, and meets the stringent requirements of localized differential privacy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122369758A_ABST
    Figure CN122369758A_ABST
Patent Text Reader

Abstract

This invention provides a localized differential privacy protection method for medical data. It employs a perturbation algorithm to perturb the data, with the privacy budget set as follows: sensitivity levels are applied to the relevant disease types; based on the sensitivity level, a corresponding privacy budget is set for each disease, where higher sensitivity levels correspond to smaller privacy budget values. This invention assesses disease sensitivity from multiple dimensions, including genetic risk, social discrimination, and treatment costs, achieving differentiated dynamic privacy budget allocation. Smaller values ​​are allocated to highly sensitive diseases to enhance privacy protection, while larger privacy budget values ​​are allocated to less sensitive diseases to reduce data distortion. This solves the problem of insufficient targeted protection caused by fixed privacy budgets in existing methods. Furthermore, the accuracy against background knowledge attacks is significantly lower than 1.2 times that of random guessing, and the privacy protection effect meets the stringent requirements of the formal definition of localized differential privacy.
Need to check novelty before this filing date? Find Prior Art