Secure Computation System for Fisher Exact Test
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for computing Fisher's exact test require significant computational resources due to repeated references to large tables, especially in secure computation scenarios where genome information needs to be kept secret, leading to inefficiencies and potential data breaches.
Innovation Solution
A secure computation system with multiple devices that preprocesses and secures frequency values, using batch-reading algorithms to efficiently compute function values without disclosing raw frequencies, thereby reducing computational overhead and maintaining data secrecy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional secure computation methods are used to compute Fisher's exact test, then data security is maintained, but computational efficiency deteriorates due to repeated references to large tables
Solution Approach 1:
The patent applies preliminary action by precomputing factorials and logarithmic factorial values and storing them in lookup tables before the actual Fisher's exact test computation. This allows the secure computation process to directly reference precomputed values rather than calculating them repeatedly, significantly improving computational efficiency while maintaining data security through encrypted table access
Solution Approach 2:
The patent creates encrypted copies of the lookup tables containing precomputed factorial and logarithmic factorial values. These encrypted tables can be referenced multiple times during secure computation without decrypting the underlying data, allowing efficient repeated access while maintaining security. The tables are copied and distributed to participating parties for local access
2Loss of time
If the number of table references is reduced, then computational overhead decreases, but the complexity of the secure computation protocol increases
Solution Approach 1:
The patent merges multiple computational operations into a unified secure protocol framework. By combining the secure access to precomputed factorial tables, logarithmic factorial tables, and the Fisher's exact test computation into a single integrated secure computation process, it reduces the number of separate table references and cryptographic operations needed, thereby reducing computational overhead while managing protocol complexity
3Productivity
If precomputed tables are used to improve efficiency, then computation speed increases, but memory requirements increase
Solution Approach 1:
The patent extracts only the essential precomputed values (factorials and logarithmic factorials) needed for Fisher's exact test into separate lookup tables, rather than storing all possible computation results. This selective extraction minimizes memory requirements while still providing the necessary precomputed data to speed up the actual test computation, balancing memory usage with computational efficiency
Data Source
AI summary
Fisher's exact test is efficiently computed through secure computation. A computation range determination part determines i0, i1, x0, x1. A preliminary computation part computes f(x0), . . . , f(x1), and generates an array M=(f(x0), . . . , f(x1)). A securing part secures the array M, and generates a secure text array <M>=(<f(x0)>, . . . , <f(x1)>). A batch-reading part generates a function value secure text (<f(ai)>, <f(bi)>, <f(ci)>, <f(di)>) (i0≤i≤i1).