PCM In-Memory Data Sanitization Using AI Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data processing systems face inefficiencies in identifying and sanitizing sensitive data, leading to resource-intensive processing, delays, and increased risk of data breaches due to reliance on central repositories and lack of real-time processing capabilities.
Innovation Solution
Integration of Artificial Intelligence (AI) and Machine Learning (ML) with Phase Change Memory (PCM) technology to dynamically identify and sanitize sensitive data within the memory, eliminating the need for central repositories and enabling in-memory processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional data processing systems check every incoming record to determine sanitization requirements, then data privacy and security are maintained, but computational resources and processing time are significantly consumed
Solution Approach 1:
The system performs preliminary classification of data records into sensitive and non-sensitive categories using machine learning models before the actual sanitization process. This preliminary action filters out non-sensitive records that do not require sanitization, reducing the computational burden while maintaining security for records that do need processing.
Solution Approach 2:
The system uses self-learning machine learning models that automatically adapt to new data patterns and classification requirements without manual retraining. The models continuously improve their accuracy in identifying sensitive data, enabling the system to maintain high security standards while processing data more efficiently over time.
2Ease of operation
If a central repository is used to store and manage sanitized data references, then data management is centralized, but system performance deteriorates and resource burden increases
Solution Approach 1:
The system extracts the data management function from a centralized repository and distributes it across multiple processing nodes. Each node independently manages its own data sanitization and storage, eliminating the single point of failure and performance bottleneck associated with centralized repositories while maintaining operational simplicity.
Solution Approach 2:
The system segments the data management task into separate functional modules: classification, sanitization, and storage. These modules can be distributed across different processing nodes, allowing parallel processing and reducing the resource burden on any single central repository, thereby improving overall system performance.
3Reliability
If exhaustive search through all records is performed to identify sensitive data, then data privacy is ensured, but processing time is prolonged and computational resources are increased
Solution Approach 1:
The system performs preliminary classification using machine learning models to identify and separate sensitive records from non-sensitive records before the exhaustive search process. This preliminary action reduces the search space significantly, allowing the system to maintain comprehensive privacy checks for sensitive data while avoiding time-consuming processing of non-sensitive records.
Solution Approach 2:
The system incorporates feedback mechanisms where the machine learning models continuously learn from processed data and improve their classification accuracy. This feedback loop enables the system to become more efficient over time, reducing the computational resources and processing time required while maintaining high standards of data privacy and security.
Data Source
AI summary
Systems and methods for intelligent data sanitization employing PCM and AI/ML are provided. The idea uses AI/ML to detect specific facts that needs sanitization rather than full properties in incoming records. Data sanitization is optimized using this focused method, saving computational resources. To properly manage changing data volumes, PCM shifts between Logical 0 and Logical 1 states. Logical 0 processes smaller volumes with high resistance and low conductivity, while Logical 1 processes large volumes with low resistance and high conductivity. The AI/ML module organizes and directs data to maximize resource and processing efficiency. The PCM processes data in-memory and directly overwrites, eliminating erasure. AI/ML and PCM integrate to sanitize data quickly, efficiently, and securely, improving system performance and data integrity without a central repository. The system dynamically adjusts to changing data patterns, protecting and optimizing data.