Personalized Data Disturbance Device for Privacy and Usability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing privacy protection techniques, such as k-anonymization and differential privacy, generalize data more than necessary, degrading usability and failing to protect privacy according to individual needs.
Innovation Solution
A data disturbance device that calculates a disturbance parameter to irreversibly convert acquired data, allowing for personalized privacy protection while maintaining data usability, using a method that minimizes mutual information between raw and processed data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If k-anonymization or differential privacy techniques are used to protect privacy, then privacy protection is improved, but data usability is degraded due to excessive generalization
Solution Approach 1:
The patent applies local quality by allowing different disturbance parameters to be applied to different data items or different individuals. Each data item can be disturbed according to its specific sensitivity and the individual's privacy needs, rather than applying uniform generalization to all data. This enables selective privacy protection that maintains usability for less sensitive data while protecting sensitive data.
Solution Approach 2:
The patent implements dynamics by making disturbance parameters adjustable and adaptable. The system can dynamically modify disturbance levels based on individual privacy preferences, data sensitivity assessments, and usage contexts. This allows the privacy protection mechanism to adapt to changing requirements without requiring excessive generalization that would degrade overall data usability.
2Reliability
If uniform privacy protection techniques are applied to all data, then privacy protection is improved, but the ability to protect privacy according to individual needs is lost
Solution Approach 1:
The system applies different disturbance parameters to different individuals and data items based on their specific privacy needs and sensitivity. Each individual can have customized privacy protection levels for different types of data, allowing personalized privacy protection rather than uniform treatment of all data.
Solution Approach 2:
The disturbance parameters are designed to be dynamically adjustable for each individual and data item. The system can adapt the level and type of disturbance based on individual preferences, data sensitivity classifications, and contextual factors, enabling versatile personalized privacy protection.
3Reliability
If data is disturbed to meet differential privacy standards, then privacy safety is improved, but statistical information quality is degraded
Solution Approach 1:
The patent changes the parameters of data disturbance by using individualized disturbance parameters rather than fixed additive noise. By adjusting parameters such as disturbance magnitude, type, and application scope based on data sensitivity and individual needs, the system can achieve privacy protection while minimizing degradation of statistical information quality.
Solution Approach 2:
The system dynamically adjusts disturbance parameters to balance privacy protection with statistical information quality. By making parameters adaptive rather than static, the system can apply stronger disturbance where needed for privacy safety while applying minimal or no disturbance to data where statistical precision is critical, thereby maintaining overall statistical information quality.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This invention is concerning a data disturbance device capable of protecting privacy according to the needs of each individual while maintaining data usability. The data disturbance device has a disturbance object setting unit that calculates a disturbance parameter necessary to disturb information, which is set as information to be disturbed, out of items of information contained in acquired data, and a data disturbance unit that generates disturbed data by irreversibly converting the acquired data using the disturbance parameter.