Synthetic Data Privacy Screening for Membership Inference Risk

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional privacy methods for protecting individual identities in databases are time and labor intensive, requiring domain expertise and are ineffective against sophisticated malicious actors who can reidentify individuals using quasi-identifiers, despite anonymization techniques.

Innovation Solution

A data privacy system uses machine learning to automatically identify quasi-identifiers by ranking attributes based on feature importance and iteratively applying a classification model to determine similarity, and assesses susceptibility to membership inference attacks by generating synthetic data and training classifiers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional privacy methods are used to protect individual identities in databases, then privacy protection is provided, but the methods are time and labor intensive and require high levels of domain expertise

Engineering Contradiction:

Improveprivacy protection effectivenessVSAvoidtime and labor intensity

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual, mechanical privacy protection methods with an automated machine learning system. The system uses algorithms to automatically identify quasi-identifiers and assess membership inference attack susceptibility, eliminating the need for manual domain expertise and significantly reducing time and labor requirements while maintaining or improving privacy protection effectiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If anonymization techniques are applied to protect individual identities, then privacy is protected, but sophisticated malicious actors can still reidentify individuals using quasi-identifiers

Engineering Contradiction:

Improveprivacy protection effectivenessVSAvoidreidentification risk

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by proactively identifying quasi-identifiers and assessing membership inference attack susceptibility before malicious actors can exploit them. The system preemptively flags attributes that could be used for reidentification, allowing organizations to take corrective privacy保护措施 before attacks occur, rather than reacting after breaches happen.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring and assessing the susceptibility of synthetic data to membership inference attacks. By providing feedback on which attributes pose reidentification risks, the system enables iterative improvement of privacy protection measures, allowing organizations to adjust their anonymization strategies based on actual vulnerability assessments.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If manual domain expertise is required for privacy protection, then accurate identification of quasi-identifiers is achieved, but the process becomes time and labor intensive

Engineering Contradiction:

Improvequasi-identifier identification accuracyVSAvoidprocessing efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent substitutes manual domain expertise with automated machine learning algorithms that can identify quasi-identifiers with high accuracy. The system uses supervised learning models trained to recognize patterns indicative of quasi-identifiers, automatically performing the task that previously required expert human analysis, thereby maintaining measurement precision while dramatically improving productivity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the machine learning model to autonomously identify quasi-identifiers and assess privacy risks without requiring continuous human intervention or domain expertise. The automated system serves itself by processing data, making decisions, and providing recommendations, freeing human experts from routine analysis tasks and enabling them to focus on complex strategic decisions.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20260044534A1Detection of Susceptibility of Membership Inference Attacks on Synthetic Data

Publication Date: 2026.02.12 PROTEGRITY US HLDG LLC

AI summary

A data privacy system automatically determines quasi-identifiers in a database containing individuals' records. The data privacy system applies a machine learning model to the database, the model configured to classify each record in the database and output a measure of its confidence in its classification. The data privacy system determines, based on the measure of confidence, how important each attribute is to the model's classification. The data privacy system iteratively applies a machine learning model on a modified database that includes the highest ranked attributes to identify the quasi-identifiers in the records in the database. The data privacy system can use identified quasi-identifiers to determine if the database is susceptible to a membership inference attack, and in response to such a determination, can perform one or more data privacy operations on the database to reduce this risk.