Secure Statistical Processing via Cross-Tabulation Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing secure computation methods are slow and impractical for performing statistical processing, such as logistic regression analysis, due to the inclusion of operations like division and exponential functions, which hinder efficient parameter calculation.
Innovation Solution
A secure statistical processing system that generates a cross tabulation table with frequencies in plain text, allowing normal computation to handle slow operations like division and exponential functions while maintaining record privacy, thereby accelerating statistical processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If secure computation is used to perform statistical processing operations (division, exponential functions), then data privacy is protected, but processing speed becomes too slow for practical use
Solution Approach 1:
The patent segments the statistical processing into two distinct parts: (1) cross-tabulation computation that requires secure computation to protect individual record privacy, and (2) statistical parameter computation (division, exponential functions) that can be performed on aggregated frequency data. This segmentation allows each part to use the most appropriate computation method for its requirements.
Solution Approach 2:
The patent extracts the statistical processing operations (division, exponential functions) from the secure computation environment and performs them on plain-text frequency data in the cross-tabulation table. This extraction eliminates the need to perform these operations under encryption, dramatically improving speed while maintaining privacy protection through the secure cross-tabulation generation.
2Loss of information
If secure computation is used for all operations including division and exponential functions, then data confidentiality is maintained, but computation time exceeds practical timeframes
Solution Approach 1:
The patent performs preliminary secure computation to generate the cross-tabulation table with frequency data in plain text form. Once this preliminary secure processing is complete, subsequent statistical operations can be performed efficiently on the already-processed frequency data without requiring continued secure computation, thus reducing total computation time.
Solution Approach 2:
The cross-tabulation frequency table serves as an intermediary data structure that bridges secure data processing and efficient statistical computation. The frequency data in plain text acts as a mediator that allows fast statistical operations while the secure generation of this table ensures confidentiality of the underlying individual records.
Data Source
AI summary
Provided is a technique for performing statistical processing such as processing for obtaining parameters of logistic regression analysis faster than before. A secure statistical processing system includes a cross tabulation table computing device 2 that performs secure computation on a cross tabulation table in which frequencies are in plain texts while keeping each record concealed; and a statistical processing device 3 that performs predetermined statistical processing using the cross tabulation table in which frequencies are in plain texts. The cross tabulation table computing device 2 may include a plurality of secure computation devices 221, . . . , 22N that perform secure computation on a cross tabulation table in which frequencies are fragments subjected to secret sharing while keeping each record concealed, and a management device 21 that restores the fragments to compute the cross tabulation table in which frequencies are in plain texts.