Database Privacy Protection Using Kurtosis-Based Distribution Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current privacy preservation methods for databases, such as k-anonymity and l-diversity, are computationally complex and result in significant utility loss, making them inefficient for protecting sensitive data while maintaining privacy.
Innovation Solution
A method and system that determine the distribution pattern of sensitive attributes using Kurtosis measurement, comparing adversary information gains between k-anonymity and k-anonymity l-diversity models, and optimizing k and l values to apply the k-anonymity model when the distribution is leptokurtic, reducing complexity and information loss while maintaining privacy protection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If k-anonymity and l-diversity methods are applied for privacy preservation, then privacy protection is enhanced, but computational complexity increases significantly
Solution Approach 1:
The patent changes the parameter of distribution pattern recognition (identifying leptokurtic distributions) to determine when simpler k-anonymity is sufficient, avoiding the need for computationally intensive l-diversity while maintaining equivalent privacy protection. This parameter-based decision rule resolves the contradiction by adapting the complexity of the privacy preservation method to the actual data characteristics.
2Reliability
If k-anonymity and l-diversity methods are applied for privacy preservation, then privacy protection is enhanced, but utility loss increases
Solution Approach 1:
The patent uses distribution pattern parameters (kurtosis measurement) to determine the appropriate privacy preservation method. When leptokurtic distribution is detected, it applies only k-anonymity which causes less utility loss compared to l-diversity, while still achieving the required privacy protection level. This resolves the contradiction by selecting the least intrusive method that satisfies privacy requirements.
3Reliability
If suppression technique is applied to control sensitive information flow, then privacy protection is improved, but data quality is drastically reduced
Solution Approach 1:
The patent extracts and analyzes the distribution pattern characteristics (kurtosis) of sensitive attributes to determine the appropriate privacy preservation approach. By extracting this key parameter, it avoids blanket suppression of data and instead applies targeted privacy methods that preserve data quality while protecting privacy.
Solution Approach 2:
The patent changes from a binary suppression approach to a parameter-based selective approach, using kurtosis measurement to determine when to apply privacy preservation and which method to use. This maintains data quality by avoiding unnecessary suppression while still protecting privacy when needed.
Data Source
AI summary
The invention relates to a system and a method for privacy preservation of sensitive attributes stored in a database. The invention reduces the complexity and enhances privacy preservation of the database by determining the distribution of sensitive data based on Kurtosis measurement. The invention further determines and compares the optimal value of k-sensitive attributes in k-anonymity data sanitation model with the optimal value of I sensitive attributes in / diversity data sanitation model using adversary information gain. The invention reduces the complexity of the method for preserving privacy by applying k anonymity only, when the distribution of the sensitive data is leptokurtic and optimal value of k is greater than the optimal value of /.