Autoencoder-Based Data Access Policy Adjustment for Derived Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data analytics systems rely on human experts to manually set data access policies for derived data, leading to inconsistent results and over- or under-protection, as they fail to account for the difficulty of recovering original data from derived data.
Innovation Solution
An autoencoder network is used to measure reconstruction error and complexity, generating a level of difficulty score that adjusts data access policies automatically based on the initial data access policy level and the complexity of recovering original data from derived data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If human experts manually set data access policies for derived data, then flexibility in policy creation is maintained, but consistency and accuracy of policy enforcement deteriorate due to human error and inability to assess recovery difficulty
Solution Approach 1:
The system performs self-service by automatically generating data access policies through the autoencoder network without requiring manual human intervention. The network autonomously assesses recovery difficulty and generates appropriate policies, eliminating human error while maintaining operational flexibility through automated decision-making
Solution Approach 2:
The patent replaces the mechanical human decision-making process with an automated neural network system. The autoencoder network substitutes human experts in assessing recovery difficulty and determining access policies, providing consistent and accurate measurements that human manual processes cannot achieve
2Adaptability or versatility
If human experts manually assess recovery difficulty, then subjective judgment is applied, but objective measurement precision deteriorates due to inability to quantify recovery difficulty
Solution Approach 1:
The patent replaces subjective human judgment with an automated neural network measurement system. The autoencoder network objectively quantifies recovery difficulty by measuring reconstruction error, providing precise numerical assessments that substitute imprecise human subjective evaluations
Solution Approach 2:
The system changes the assessment parameter from subjective human judgment to objective reconstruction error measurement. By using the autoencoder network to calculate quantitative reconstruction error metrics, the system transforms the abstract concept of recovery difficulty into a measurable parameter that can be precisely evaluated and compared
3Ease of manufacture
If data access policies are manually configured without considering recovery difficulty, then policy creation is simple, but data protection reliability deteriorates due to over- or under-protection
Solution Approach 1:
The system performs self-service by automatically generating appropriate data access policies based on recovery difficulty assessment. The autoencoder network autonomously determines policy parameters without manual configuration, ensuring consistent and reliable protection while eliminating the complexity of manual policy creation
Solution Approach 2:
The system implements feedback by using the autoencoder network to continuously assess recovery difficulty and adjust data access policies accordingly. The reconstruction error measurement provides feedback on the actual recoverability of data, enabling dynamic policy adjustment that maintains reliable protection while adapting to different data characteristics
Data Source
AI summary
From a first model parameter, an autoencoder network is generated. A reconstruction error for the autoencoder network is measured, the reconstruction error comprising a difference between an input to the autoencoder network and a corresponding output from the autoencoder network, the input to the autoencoder network comprising a portion of an initial set of data. The reconstruction error and a confidence score corresponding to a complexity level of the autoencoder network are aggregated into a level of difficulty score of the autoencoder network. From the level of difficulty score and an initial data access policy level corresponding to the initial set of data, a derived data access policy level corresponding to the initial data access policy level is generated, the derived data access policy level enforcing access to a transformed set of data generated by applying a transformation to the initial set of data.