Privacy-Preserving User Data Collection via Trusted Execution Environment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The collection of user data by electronic devices raises security and privacy concerns due to the potential misuse of personal information, as users desire personalized services while being hesitant to share identifying data.
Innovation Solution
A system and method for privacy-preserving user data collection, where user data is transformed using local differential privacy within a trusted execution environment (TEE) before being sent to a service provider, ensuring that the data is altered to prevent misuse while still being usable for training models and generating personalized services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If user data is collected and shared with service providers for personalized services, then service personalization is improved, but user privacy and security are worsened
Solution Approach 1:
A trusted execution environment (TEE) acts as an intermediary between the application and the service provider. The TEE securely transforms user data using local differential privacy before transmission, preventing both the application and service provider from accessing raw personal information while still enabling personalized services through the transformed data
Solution Approach 2:
The system intentionally introduces controlled noise into user data through local differential privacy transformation. This deliberate degradation of data precision protects individual privacy while preserving aggregate statistical properties, converting the potential harm of data exposure into a benefit for privacy protection
2Loss of information
If raw user data is transmitted to service providers, then data utility for training models is improved, but security and privacy protection is worsened
Solution Approach 1:
The system performs data transformation using local differential privacy before transmitting data to service providers. This preliminary action ensures that privacy protection is built into the data itself before it leaves the user's device, rather than relying on security measures at the service provider end
Solution Approach 2:
The TEE transforms user data by changing its parameters through local differential privacy transformation, adding controlled noise and modifying the data structure. This changes the data from a high-utility raw format to a protected format that maintains statistical properties while eliminating identifiable personal information
3Reliability
If data transformation is applied to protect privacy, then privacy protection is improved, but data quality and personalization accuracy is worsened
Solution Approach 1:
Local differential privacy is applied at the individual user data level rather than aggregating data first. Each user's data is independently transformed with appropriate noise, ensuring strong privacy protection for each individual while the collection of transformed data maintains sufficient statistical power for accurate personalization
Data Source
AI summary
A method includes obtaining, by an application executing on a processor of an electronic device, user data of a user, generating a representation of the user data, applying local differential privacy to the representation of the user data, to generate a transform of the representation of the user data, sending the transform of the representation of the user data, to a service provider via a network and receiving, from the service provider, via the network, service data based on the transform of the user data. The service data includes a user-specific output based on the transform of the user data. The application executes outside of a trusted execution environment (TEE) of the electronic device. The transform of the representation of the user data is generated in the TEE of the electronic device.