Mobile Communication Data Sanitization for Private Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The application of machine learning technology in mobile communication systems raises concerns regarding data security and privacy, particularly when using security or privacy target data for training and inference processes.
Innovation Solution
A communication method is implemented where user equipment transmits training and inference data to a network apparatus, which deletes security and privacy target data before transmitting it to another user equipment, ensuring that only data without sensitive information is used for machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning technology is applied to wireless communication air interface, then communication performance is improved, but data security and privacy are compromised
Solution Approach 1:
The patent extracts and removes security target data and privacy target data from the training data and inference data before transmission to the second user equipment. This ensures that only data without sensitive information is used for machine learning operations, thereby maintaining communication performance while eliminating data security and privacy risks.
Solution Approach 2:
The network apparatus acts as an intermediary between the first user equipment and the second user equipment. It receives training data and inference data from the first user equipment, deletes sensitive information, and then transmits the cleaned data to the second user equipment. This intermediary role enables the system to maintain both communication performance and data security.
2Measurement precision
If training data and inference data are transmitted for machine learning, then learning accuracy is improved, but sensitive information is exposed
Solution Approach 1:
The network apparatus extracts and removes security target data and privacy target data from the training data and inference data. This extraction process maintains the utility and accuracy of the machine learning model while eliminating sensitive information exposure, as only non-sensitive data is transmitted to the second user equipment.
3Object-affected harmful factors
If data deletion is performed by network apparatus, then privacy is protected, but data processing complexity increases
Solution Approach 1:
The network apparatus serves as an intermediary that handles the data deletion process. By centralizing this function in the network apparatus, the complexity of privacy protection is managed at a dedicated level, and the first and second user equipment can focus on their primary functions without implementing complex deletion mechanisms themselves.
Data Source
AI summary
The present disclosure relates to a communication method in a mobile communication system. The communication method includes a step of transmitting, by a first user equipment, training data and/or inference data to a network apparatus. The communication method includes a step of deleting, by the network apparatus, security target data and/or privacy target data from the training data and/or the inference data. The communication method includes a step of transmitting, by the network apparatus, the training data after deletion and/or the inference data after deletion to a second user equipment. The communication method includes a step of performing, by the second user equipment, machine learning using the training data after deletion and/or the inference data after deletion.