Private ID Bucket Matching for Scalable MPC Computation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing secure multiparty computation (MPC) protocols are inefficient and resource-intensive when computing functions on large datasets, as they require recomputing private identifiers for each function, reducing scalability and wasting system resources.
Innovation Solution
The technique involves storing private identifiers in buckets by entities and using bucket identifiers to determine common identifiers, reducing the need for repeated computations by the MPC protocol.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If MPC protocols recompute private identifiers for each function on large datasets, then data privacy is preserved, but computational efficiency and resource usage deteriorate
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing private identifiers in bucket data structures before function execution. Entities organize their private identifiers into buckets based on grouping criteria, allowing the MPC protocol to directly retrieve pre-computed identifiers during function execution rather than recomputing them each time, thus improving computational efficiency while maintaining privacy
Solution Approach 2:
The patent applies segmentation by dividing private identifiers into multiple buckets based on grouping criteria. This segmentation allows the system to work with smaller, organized subsets of data rather than processing all private identifiers uniformly, reducing the computational burden on the MPC protocol while preserving the ability to maintain data privacy through selective bucket access
2Measurement precision
If MPC protocols process complete datasets for each function, then computation accuracy is maintained, but resource consumption and time usage increase
Solution Approach 1:
The patent applies the taking out principle by extracting only the necessary private identifiers from the complete dataset through bucket matching. Instead of processing all private identifiers for each function, the system extracts only those identifiers that are common to both entities based on bucket identifier matches, reducing processing time while maintaining computation accuracy for the relevant subset
Solution Approach 2:
The patent applies partial action by performing computation only on the subset of private identifiers that are actually needed for the function, rather than processing the complete dataset. By using bucket identifiers to identify common elements, the system performs partial computation on relevant data subsets, reducing time consumption while maintaining accuracy for the computed results
Data Source
AI summary
Methods and systems are disclosed for performing private identification matching. The methods and systems store, by a first entity, a first set of private identifiers associated with a first set of data. The methods and systems group, by the first entity, different subsets of the first set of private identifiers into respective buckets of a first plurality of buckets according to a grouping criterion. The methods and systems apply a function to a subset of a second set of data, stored by a second entity, corresponding to private identifiers associated with one or more buckets of a second plurality of buckets, grouped by the second entity, that match private identifiers associated with one or more buckets of the first plurality of buckets. The methods and systems provide, to the first entity, a result of applying the function to the subset of the second set of data.