Privacy-Safe Distributed Data Mining Protocol
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data privacy restrictions in distributed database systems hinder the effective use of privacy-sensitive data for analysis, as they require de-identification to protect individual privacy, leading to reduced data resolution and lost information, which limits the ability to perform high-resolution queries and analyses that could benefit applications like healthcare and market research.
Innovation Solution
A Privacy Preserving Data-Mining Protocol that allows for high-resolution query and manipulation of privacy-sensitive data by using an aggregator processor to accept queries, transmit parameter lists to source-entity processors, aggregate files, and filter out sensitive information, ensuring that individual privacy is maintained while enabling comprehensive data analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If de-identification is applied to protect individual privacy, then privacy protection is improved, but data resolution and information completeness deteriorate
Solution Approach 1:
The system segments data processing into distinct phases: local filtering at source-entity processors and central aggregation at the aggregator processor. Source-entity processors filter and prepare data locally, then transmit to the aggregator which performs final aggregation and privacy verification. This segmentation allows high-resolution data to be maintained during processing while privacy protection is applied at appropriate stages without sacrificing data quality.
Solution Approach 2:
The aggregator processor acts as an intermediary between data sources and analysis consumers. It receives raw data from source-entity processors, aggregates the data while maintaining privacy through controlled access, and provides analysis results to consumers. This intermediary role enables the system to maintain data resolution while implementing privacy protection mechanisms.
2Object-affected harmful factors
If data is aggregated to preserve privacy, then privacy protection is improved, but the ability to perform high-resolution queries deteriorates
Solution Approach 1:
Source-entity processors perform preliminary filtering and preparation of data locally before transmitting to the aggregator. This preliminary action ensures that data is pre-processed according to local requirements and privacy constraints, maintaining resolution where possible while preparing for centralized aggregation that will apply additional privacy protection.
Solution Approach 2:
The system dynamically adjusts the level of aggregation and privacy protection based on query requirements and data sensitivity. The aggregator processor can perform aggregation at different levels of detail depending on the specific query and the privacy implications, allowing high-resolution queries when privacy risks are low and more aggregated data when privacy protection is critical.
3Productivity
If distributed data processing is implemented, then data availability and processing capability are improved, but system complexity increases
Solution Approach 1:
The distributed system is segmented into independent source-entity processors and a central aggregator processor. Each source-entity processor operates independently with its own data and filtering capabilities, while the aggregator coordinates the central aggregation process. This segmentation distributes computational workload and improves processing capability while keeping individual component complexity manageable through clear functional separation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A Double Blinded Privacy-Safe Distributed Data Mining Protocol is disclosed, among an aggregator, a data consumer entity having privacy-sensitive information, and data source entities having privacy-sensitive information. The aggregator does not have access to the privacy-sensitive information at either the data consumer entity or the data source entities. The aggregator formulates a query without using privacy-sensitive information, and sends the query to the data consumer entity. The data consumer entity generates a list of specific instances that meet the conditions of the query and sends the list, encrypted, to the data source entities either directly or through the aggregator. The data source entities match the list against transactional data, de-identify the matched results, and send them to the aggregator. The aggregator combines results from data source entities and sends the combined result to the data consumer entity. This allows for privacy-safe data mining where both the data consumer entity and data source entities have privacy-sensitive information not available for the aggregator to see or use.