Format-Preserving Data Obfuscation via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

There is a need for a system that can obfuscate electronic data while preserving its original format to prevent unauthorized access, especially in organizations handling sensitive information, and existing solutions do not effectively manage resource strain associated with format preservation.

Innovation Solution

The system employs a machine learning engine to analyze decision factors, including data sensitivity and available computational resources, to dynamically determine the application of format-preserving obfuscation algorithms, ensuring data masking without overstraining resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If format-preserving obfuscation algorithms are applied to all data values, then data privacy and format integrity are improved, but computational resource strain and processing time increase

Engineering Contradiction:

Improvedata privacy and format integrityVSAvoidcomputational resource strain

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies different obfuscation strategies to different data values based on their sensitivity level. High-sensitivity values receive format-preserving obfuscation algorithms, while low-sensitivity values use simpler obfuscation methods. This local differentiation resolves the contradiction by concentrating computational resources on data that most needs protection.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system dynamically determines which obfuscation algorithms to apply based on real-time analysis of data sensitivity and available computational resources. The machine learning engine continuously evaluates decision factors and adjusts the obfuscation approach accordingly, allowing the system to adapt to changing resource constraints while maintaining security.

Inventive Principle:

Principle #15Dynamics

2Reliability

If multiple obfuscation algorithms are applied to maximize security, then data protection is improved, but processing time and computational complexity increase

Engineering Contradiction:

Improvedata protectionVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system applies the minimum necessary obfuscation action required for adequate protection rather than uniformly applying maximum obfuscation to all data. By using machine learning to identify the exact protection level needed for each data value, the system avoids excessive computational time expenditure while maintaining sufficient security.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The machine learning engine performs preliminary analysis of data sensitivity and computational resource availability before selecting obfuscation algorithms. This preliminary determination allows the system to pre-plan the most efficient obfuscation sequence, reducing overall processing time while ensuring adequate protection.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If format-preserving techniques are used for all data, then data usability and format integrity are improved, but system performance and processing efficiency deteriorate

Engineering Contradiction:

Improvedata usabilityVSAvoidsystem performance

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system reserves format-preserving obfuscation techniques for data values where this level of protection is necessary, while using more efficient obfuscation methods for less sensitive data. This localized application maintains data usability for critical information without sacrificing overall system performance.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the obfuscation parameters and algorithms based on the sensitivity level and characteristics of each data value. By adjusting these parameters dynamically, the system achieves the right balance between data usability and processing efficiency for each specific case.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12105827B2System for secure obfuscation of electronic data with data format preservation

Publication Date: 2024.10.01 BANK OF AMERICA CORP

AI summary

Embodiments of the invention are directed to systems, methods, and computer program products for utilizing machine learning to identify data which is to be obfuscated in a format-preserving manner, which allows the obfuscated or masked data to appear as though it is original data. Because this type of obfuscation technique may require a higher degree of computational power than other techniques, there is a need to be able to dynamically choose when to implement format preservation based on a variety of factors. By using machine learning techniques, the present invention provides the functional benefit of analyzing both the data to be obfuscated, as well as available computational resources, to determine when it is appropriate to apply a format-preserving masking algorithm to the data. Accordingly, the present invention may ensure that organizational data is appropriately masked while preventing the resource strain associated with preserving the format of all original data.