Machine-Learning Quasi-Identifier Detection for Database Privacy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional privacy methods for protecting individual identities in databases are time and labor intensive, requiring high domain expertise, and sophisticated malicious actors can still discern identities 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 using synthetic data and binary classifiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional privacy methods are used to protect individual identities, then some level of anonymity is achieved, but the methods are time and labor intensive and require high domain expertise
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 reidentification risks, substituting human expert analysis with computational models that process data efficiently without requiring domain expertise from users.
Solution Approach 2:
The system enables automated self-service privacy protection by automatically detecting quasi-identifiers and evaluating reidentification risks without human intervention. The machine learning models autonomously analyze datasets, rank attributes by importance, and generate privacy assessments, allowing the system to protect itself and the data it processes without external expert involvement.
2Reliability
If data is transformed to protect individual privacy, then anonymity is improved, but sophisticated malicious actors can still discern identities using quasi-identifiers
Solution Approach 1:
The system performs preliminary action by proactively identifying quasi-identifiers and assessing reidentification risks before data is released or used. The machine learning models evaluate potential privacy breaches in advance, allowing data protectors to take preventive measures such as removing or masking identified quasi-identifiers before the data becomes vulnerable to malicious attacks.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring and reassessing datasets to detect new quasi-identifiers that may emerge. The machine learning models provide ongoing feedback about privacy risks, allowing dynamic adjustment of protection strategies and ensuring that anonymization remains effective even as data is transformed or combined with external information sources.
3Measurement precision
If more attributes are included in the database to improve classification accuracy, then the ability to distinguish records improves, but the risk of reidentification increases
Solution Approach 1:
The system changes parameters by dynamically adjusting the selection of attributes based on their quasi-identifier importance scores. The machine learning models evaluate multiple attributes and selectively include only those necessary for classification while excluding attributes that would significantly increase reidentification risk. This parameter optimization allows the system to maintain classification accuracy while minimizing privacy harms.
Data Source
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.