Bloom Filter Data Identification Intersection Privacy Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the scenario of joint processing of multi-party data, the data identification intersection shared between data providers leads to privacy protection issues, as the intersection can be leaked to all providers, allowing them to deduce each other's data identifications.
Innovation Solution
A method involving the use of a Bloom Filter to determine a data identification intersection between databases of data providers, where a Bloom vector is constructed based on the intersection and sent to the providers, allowing them to filter and send candidate data without directly sharing the intersection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the data identification intersection is shared between data providers to enable joint data processing, then data alignment and processing efficiency are improved, but privacy protection is worsened as the intersection can be leaked to all providers
Solution Approach 1:
The patent introduces a third party (data processing device) as an intermediary to determine the data identification intersection. This intermediary calculates the intersection between data providers' databases and distributes only the necessary information through Bloom filters, preventing direct sharing of the intersection between providers while enabling joint data processing.
Solution Approach 2:
The patent uses Bloom filters to create a compressed representation (copy) of the data identification intersection. Instead of sharing the complete intersection directly, the system distributes Bloom filter structures that contain hashed information about the intersection, allowing providers to query without revealing the full intersection to each other.
2Ease of operation
If the complete data identification intersection is distributed to data providers, then data alignment is achieved, but the probability of reversing the original intersection increases
Solution Approach 1:
The patent extracts only the essential hashing information from the complete data identification intersection and distributes this extracted information through Bloom filters. This extraction process removes the direct mapping between the intersection and the original data identifications, making it difficult to reverse while maintaining the ability to align data.
Solution Approach 2:
The patent transforms the data identification intersection from its original form into a transformed representation using Bloom filter hashing. This parameter change converts the explicit intersection into a hashed structure where the original identifications cannot be easily recovered, while still enabling effective data alignment through the hash-based queries.
Data Source
AI summary
A method for data acquisition, a device and a storage medium are provided. The method includes: determining a data identification intersection between databases of data providers, where the data identification intersection comprises data identifications that are same between the databases of the data providers; constructing a Bloom vector of a Bloom Filter according to the data identification intersection, and sending the Bloom vector to the data providers; receiving candidate data sent by the data providers, where the candidate data is data corresponding to a target data identification, and the target data identification is determined by the data providers from data identifications of respective databases through the Bloom Filter based on the Bloom vector; and selecting target data corresponding to the data identification intersection from the candidate data.