Mobility Dataset Privacy Risk Scoring for Location Anonymization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to balance the provision of location-based services with maintaining user anonymity, as data from infrastructure monitoring and crowd-sourcing can be mined to reveal sensitive information, and conventional privacy measures fail to account for the privacy risks introduced by mobility patterns.
Innovation Solution
A method and apparatus are provided to analyze datasets and compute a privacy risk score by identifying common features, aggregating privacy risk values, and applying anonymization algorithms to ensure that the privacy risk score meets predetermined values before providing location-based services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If location data from infrastructure monitoring and crowd-sourcing is collected and analyzed, then location-based services can be provided with high accuracy, but user privacy is compromised as data can be mined to reveal sensitive information and mobility patterns
Solution Approach 1:
The patent introduces privacy risk scores and anonymization algorithms as intermediary mechanisms between raw location data and location-based services. These intermediaries process and transform location data to eliminate privacy risks while preserving location accuracy, allowing services to be provided without directly exposing sensitive user information
Solution Approach 2:
The patent transforms location data by changing its parameters through anonymization algorithms that modify data characteristics. The privacy risk score serves as a parameter that determines the level of anonymization applied, dynamically adjusting data transformation to balance privacy protection with service utility
2Object-affected harmful factors
If data is anonymized using conventional algorithms, then some privacy protection is achieved, but mobility patterns can still be inferred and privacy risks remain
Solution Approach 1:
The patent implements a feedback mechanism where privacy risk scores are calculated based on common features between datasets, and this feedback drives iterative anonymization. The system continuously evaluates privacy risks and adjusts anonymization parameters to eliminate mobility pattern inference while maintaining essential location information
Solution Approach 2:
The patent performs preliminary anonymization and privacy risk assessment before data is used for location-based services. By pre-processing data to remove privacy risks and validate anonymization effectiveness, the system prevents mobility pattern inference before it can occur
3Object-affected harmful factors
If strict anonymization is applied to protect privacy, then privacy risks are reduced, but the utility and accuracy of location-based services deteriorate
Solution Approach 1:
The patent introduces dynamic anonymization where the level of data transformation is adjusted based on privacy risk scores. Rather than applying fixed strict anonymization, the system dynamically adapts anonymization parameters to achieve the minimum necessary privacy protection while preserving location-based service utility and accuracy
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments described herein relate to establishing a privacy risk score between two datasets based on features common to the datasets. Methods may include: receiving a first dataset of probe data points defining a trajectory; receiving a second dataset of the probe data points defining the trajectory; identifying a plurality of features common to the first dataset and the second dataset; computing a privacy risk value for the identified features common to the first dataset and the second dataset; and computing an aggregate privacy risk score between the first dataset and the second dataset.