Machine Learning Authorization Model for Resource Access Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining authorized access to resources in computer systems is complicated due to inaccurate data and varying rules, making it difficult to identify authorized requests amidst exponentially increasing resource requests.
Innovation Solution
A system that processes resource requests using a machine-learning model trained with key-value pairs extracted from requests and augmenting data, generating authorization outputs to flag and inhibit unauthorized access by identifying patterns and relationships between entities and events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional authorization rules are used to determine authorized access, then authorization decisions can be made based on predefined rules, but the system cannot accurately identify authorized requests amidst exponentially increasing resource requests due to inaccurate data and varying rules
Solution Approach 1:
The patent replaces traditional mechanical rule-based authorization systems with a machine learning model that automatically learns authorization patterns from data. The ML model processes requests using learned representations rather than predefined rules, enabling accurate authorization decisions at scale without manual rule configuration.
Solution Approach 2:
The system transforms authorization data into different parameter representations through feature extraction and embedding. Requests are converted into numerical vectors that capture essential authorization characteristics, allowing the ML model to process and compare requests efficiently while maintaining decision accuracy.
2Reliability
If more data is collected from multiple sources to improve authorization accuracy, then the system can make better authorization decisions, but the system complexity increases due to integrating multiple data sources and processing large volumes of data
Solution Approach 1:
The patent creates a universal authorization system where a single machine learning model handles multiple data sources and various authorization scenarios. The model learns generalizable patterns from diverse data types (device information, user behavior, request characteristics) and applies them across different resources and contexts, reducing the need for separate specialized systems.
Solution Approach 2:
The system introduces an intermediary layer that collects, standardizes, and processes data from multiple sources before feeding it to the authorization model. This intermediary data processing layer unifies different data formats and sources into a consistent representation, simplifying the overall system architecture while maintaining reliable authorization decisions.
Data Source
AI summary
A set of resource requests that each includes authorization-supporting data for receiving a requested resource can be received. For each request, augmenting data associated with part of the data is retrieved, and it is determined whether access is authorized based on the augmenting data and the authorization-supporting data. A machine-learning model is trained using representations of the set of resource requests and the authorization determinations. Additional requests are processed by the trained model to generate corresponding authorization outputs. One or more identifiers to flag for inhibition of resource access are determined based on the authorization outputs. Upon detecting that a new resource request to access a particular resource includes an identifier of the one or more identifiers, a new authorization output is generated to inhibit access to the particular resource.