On-Demand AI Model for Mobile Data Sanitization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data sanitization systems face challenges in identifying sensitive data on mobile devices, particularly due to the large size of regex routines and the lack of adaptability in detecting abstract or unknown instances of sensitive data, which can lead to security risks and loss of control over data sanitization processes.
Innovation Solution
Implementing a bifurcated sanitization process using a machine learning model on the mobile device and a data scrubbing application on a remote server, along with an on-demand artificial intelligence model delivery format and output format that includes confidence metrics, to ensure accurate and secure sanitization of sensitive data without exposing it to unauthorized parties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If regex routines are transmitted to a remote server for processing, then the mobile device can identify sensitive data, but the device loses control over the data and security risks increase
Solution Approach 1:
The patent introduces a hybrid intermediary system where a lightweight local regex engine handles initial sensitive data detection on the mobile device, while a remote server provides supplementary regex patterns and validates results. This intermediary architecture allows the device to maintain data control locally while benefiting from remote server capabilities, resolving the contradiction between local security control and remote processing accuracy.
2Reliability
If a corpus of regex routines is stored locally on the mobile device, then sensitive data can be identified without remote transmission, but the device storage space is consumed
Solution Approach 1:
The patent segments the regex corpus into two parts: essential, frequently-used patterns are stored locally in a compressed format on the mobile device, while additional or updated patterns remain on the remote server. The local engine processes data with the stored subset, minimizing storage requirements while maintaining security control. This segmentation resolves the contradiction between local storage needs and security control.
Solution Approach 2:
The patent changes the parameter of regex storage by implementing dynamic loading and compression techniques. The system loads only necessary regex patterns into memory based on current processing needs, and uses compressed storage formats to reduce the footprint of the local corpus. This parameter change allows the device to maintain a functional local regex engine without consuming excessive storage space.
3Adaptability or versatility
If multiple regex routines are implemented to capture different types of sensitive data, then comprehensive data sanitization is achieved, but the system complexity increases
Solution Approach 1:
The patent implements a universal local regex engine that can execute multiple different regex patterns through a single unified interface. Rather than implementing separate specialized engines for each data type, the system uses one multi-functional engine that loads and executes various patterns as needed. This universality achieves comprehensive sensitive data detection coverage while minimizing system complexity.
Solution Approach 2:
The patent introduces dynamic pattern loading and activation mechanisms. The regex engine dynamically loads only the patterns relevant to the current data being processed, rather than maintaining all patterns in active memory simultaneously. This dynamic approach allows comprehensive coverage of different sensitive data types while keeping the active system complexity low, as patterns are loaded on-demand based on processing needs.
Data Source
AI summary
Methods and systems are described herein for leveraging artificial intelligence to sanitize sensitive data and prevent the data from leaving the mobile device and/or be exposed to unauthorized third parties. More specifically, methods and systems are described for a novel and unconventional architecture for a data sanitization application, a novel and unconventional delivery format for the data sanitization model, and a novel and unconventional output format of the data sanitization model.