Anonymization Engine for Minimality-Attack-Resistant Data Sets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data anonymization methods often result in loss of important data aspects, making anonymized data less useful, and are vulnerable to minimality attacks that can expose private information despite anonymization efforts.
Innovation Solution
A method involving an anonymization engine that orders and partitions data tuples into groups, ensuring compliance with privacy requirements such as l-diversity, by adding or merging buckets until the desired privacy standards are met, and removing non-compliant groups to generate data sets resistant to minimality attacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is anonymized by removing or generalizing sensitive information, then privacy protection is improved, but data utility is worsened
Solution Approach 1:
The data set is divided into multiple groups where each group contains tuples with similar quasi-identifier values. This segmentation allows the system to maintain privacy within each group while preserving more information across the entire data set, resolving the contradiction between privacy protection and data utility.
Solution Approach 2:
The system changes the parameter of group size dynamically, starting with smaller groups and progressively merging them into larger groups. This allows the system to find an optimal balance between privacy protection (smaller groups) and data utility (larger groups), preventing information loss while maintaining privacy.
2Loss of information
If the amount of anonymized data is minimized to preserve utility, then data usefulness is improved, but vulnerability to minimality attacks is worsened
Solution Approach 1:
The system dynamically adjusts group sizes during the anonymization process, starting with minimal groups and progressively merging them. This dynamic approach allows the system to maintain smaller effective group sizes that resist minimality attacks while still preserving data utility through selective merging of compatible groups.
Solution Approach 2:
The system incorporates feedback mechanisms that evaluate whether groups satisfy privacy requirements at each stage of the merging process. This feedback loop allows the system to maintain optimal group sizes that prevent minimality attacks while preserving data usefulness, resolving the contradiction between these two objectives.
3Reliability
If strict privacy requirements are enforced during anonymization, then privacy protection is improved, but data quality is worsened
Solution Approach 1:
The system dynamically adjusts group sizes based on privacy requirement satisfaction, allowing groups to grow from minimal size while continuously evaluating privacy compliance. This dynamic adjustment maintains strict privacy protection while preserving data quality by only merging groups that satisfy privacy requirements.
Solution Approach 2:
The system changes the effective privacy parameter (group size) during processing, allowing it to adapt to different privacy requirements while maintaining data quality. By progressively merging groups only when privacy requirements are satisfied, the system resolves the contradiction between strict privacy protection and data quality preservation.
Data Source
AI summary
The present disclosure is directed to systems, methods, and computer-readable storage media for generating data and data sets that are resistant to minimality attacks. Data sets having a number of tuples are received, and the tuples are ordered according to an aspect of the tuples. The tuples can be split into groups of tuples, and each of the groups may be analyzed to determine if the group complies with a privacy requirement. Groups that satisfy the privacy requirement may be output as new data sets that are resistant to minimality attacks.