User Data Protection via ML Classification and File Modification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As computing devices generate vast amounts of user data, users face challenges in maintaining privacy, with even small pieces of private information potentially being shared or leaked, leading to increased exposure and vulnerability to malicious actors.
Innovation Solution
A system and method that utilizes a hardware processor to detect user files containing personal information, generates transactional and behavioral data, applies a machine learning model to classify users, and modifies user files or behavior to protect privacy, including anonymizing user interactions through random input events and graphical user interface modifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users perform online actions and create files on computing devices, then user convenience and functionality are improved, but user privacy and data security deteriorate due to increased data collection and storage
Solution Approach 1:
The system performs preliminary actions by detecting user files and generating classifications before actual data sharing or leakage occurs. The hardware processor proactively identifies personal information in files, generates user classifications, and prepares protection measures in advance, preventing privacy breaches before they happen rather than responding after exposure.
Solution Approach 2:
The system introduces an intermediary classification layer between raw user data and external systems. The hardware processor generates user classifications based on detected files and interactions, serving as a mediator that enables privacy-preserving operations. This intermediary layer allows the system to manage and protect user data without directly exposing the underlying personal information.
2Object-affected harmful factors
If the system monitors and detects user files containing personal information, then user privacy protection is improved, but system complexity and processing requirements increase
Solution Approach 1:
The system segments the privacy protection process into distinct functional components: file detection, personal information identification, user classification generation, and behavior modification. The hardware processor divides the monitoring task into these separate stages, making the complex privacy protection system more manageable and efficient by handling each aspect independently rather than as a monolithic process.
Solution Approach 2:
The system implements self-service by automatically detecting user files, generating classifications, and modifying user behavior without requiring manual intervention. The hardware processor autonomously monitors files, applies machine learning models to generate classifications, and executes protection measures, reducing the need for user configuration and simplifying the overall system operation despite the underlying complexity.
3Measurement precision
If the system applies machine learning models to classify users based on multiple data sources, then classification accuracy and privacy protection effectiveness are improved, but data processing time and computational resources increase
Solution Approach 1:
The system applies partial action by selectively processing only the most relevant user files and data elements that contribute to classification accuracy. The hardware processor identifies and focuses on key personal information in detected files rather than uniformly processing all user data, achieving effective classification while reducing overall processing time and computational resource requirements.
4Object-affected harmful factors
If the system modifies user files and behavior to protect privacy, then user data security is improved, but user experience and operational smoothness may deteriorate
Solution Approach 1:
The system applies local quality by selectively modifying only specific user files and behaviors that pose privacy risks, rather than uniformly altering all user operations. The hardware processor identifies particular files containing personal information and targets only those for modification, leaving other user activities unchanged. This localized approach maintains data security while preserving overall user experience and operational smoothness.
Data Source
AI summary
Disclosed herein are systems and methods for protecting user data. In one aspect, an exemplary method comprises, by a hardware processor, detecting one or more user files, created by a user, that are on a user device; generating user transactional data associated with one or more detected network-based interactions with a service provider by the user, and user behavior data based on one or more user interactions with a graphical user interface of the user device by the user; generating a user classification using a machine learning model that classifies the user based on the one or more user files, the user transactional data, and the user behavior data; and when the user is identifiable based on the user classification, modifying at least one of the one or more user files stored on the user device and user behavior of the user during an operation of the user device.