AIMSDS Data Security Attribution via ML Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Financial institutions face challenges in managing and securing data collected from global sources, as they must adhere to diverse and complex data privacy laws across different countries, which requires efficient data classification, tagging, and access control.
Innovation Solution
The implementation of an Augmented Intelligent Machine for Systematic Attribution of Data Security (AIMSDS) that utilizes machine learning for real-time data classification and tagging, dynamically adapting to global regulations and user access controls, while ensuring proper data classification and security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual processes are used for data classification and tagging, then implementation is straightforward, but productivity is low and cannot handle real-time requirements
Solution Approach 1:
The patent replaces manual mechanical classification processes with an automated machine learning system that uses natural language processing and classification algorithms to automatically tag and classify data elements, achieving real-time processing without human intervention
Solution Approach 2:
The system enables self-service automation where the data classification and tagging is performed automatically by the machine learning model without requiring manual configuration or intervention, with the system learning and adapting to new data patterns autonomously
2Adaptability or versatility
If hardcoded rules are used for data classification, then the system is simple to implement, but adaptability to new regulations is poor
Solution Approach 1:
The patent implements a dynamic system where the machine learning model continuously learns from new data and regulations, automatically updating its classification rules and tags to adapt to changing regulatory requirements without requiring system reconfiguration
Solution Approach 2:
The system incorporates feedback mechanisms where classification results and regulatory changes are fed back into the machine learning model, enabling continuous improvement and adaptation of classification accuracy and regulatory compliance
3Reliability
If data is stored without classification, then storage is simple, but security and access control are compromised
Solution Approach 1:
The patent applies preliminary classification and tagging to data elements at the time of ingestion, before storage or access operations occur, enabling subsequent security and access control measures to be efficiently applied based on pre-determined data sensitivity and regulatory requirements
4Ease of operation
If access control is based on user request without systematic classification, then access is easy to implement, but compliance with data privacy laws is difficult to ensure
Solution Approach 1:
The patent introduces an intermediary classification and tagging layer between data storage and user access requests, where the system automatically determines appropriate access permissions based on data classification tags and user credentials, ensuring compliance without complicating the access process
Data Source
AI summary
Disclosed are various embodiments for augmented intelligent machine for systematic attribution of data security. A set of global regulations is received by the system. Next, at least one decision rule for mapping one or more data elements is output based at least in part on the set of dynamic global regulations. A data input is received from at least one data source. Next, the data input is parsed to determine at least one sensitive data elements. Then, a confidentiality level of at least one sensitive data element is determined. The ingesting table is joined with a drive mapping data set. Finally, at least one security policy is applied to a type of data input based at least in part on the drive mapping data set or the confidentiality level.