Graph-Based Permission Messages for Behavioral User Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer systems lack effective methods to authenticate users and distinguish between genuine users and fraudsters, particularly in scenarios involving authorization requests for operations within computer environments, often relying on static login credentials that are vulnerable to fraud.
Innovation Solution
A system utilizing a graph database and machine learning techniques, such as Hidden Markov models, to analyze user operation history and generate permission messages with correct and misleading responses, calculating an accumulated probability to determine user authenticity based on response patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If static login credentials are used for user authentication, then the authentication process is simple and fast, but the system becomes vulnerable to fraud and cannot distinguish between genuine users and fraudsters
Solution Approach 1:
The system performs preliminary analysis of user operation history and behavior patterns before authentication occurs. Historical data about user operations is collected and stored in advance, enabling the system to make informed authentication decisions based on pre-established user profiles and patterns rather than relying solely on static credentials.
Solution Approach 2:
The system continuously monitors and analyzes user operation patterns, providing feedback loops where authentication decisions are based on real-time behavior analysis. The graph database structure allows the system to update user profiles based on observed behavior, creating a dynamic authentication mechanism that adapts to changing user patterns and detects anomalies.
2Measurement precision
If comprehensive analysis of user operation history is performed using graph databases and machine learning, then user authentication accuracy is improved, but computational resources and processing time increase
Solution Approach 1:
The system segments the complex authentication analysis into manageable components using the graph database structure. Operation history is divided into discrete nodes and edges representing different operation types and relationships, allowing the system to query and analyze only the relevant portions of data needed for authentication rather than processing entire historical records at once.
Solution Approach 2:
The system applies machine learning models selectively rather than analyzing all historical data exhaustively. The graph database structure enables the system to identify and process only the partial subset of operation history that is most relevant to the current authentication decision, reducing computational overhead while maintaining high accuracy.
3Reliability
If the system analyzes multiple operation types and generates permission messages with correct and misleading responses, then fraud detection capability is enhanced, but the complexity of processing and interpreting operation data increases
Solution Approach 1:
The graph database structure applies local quality by creating specialized nodes and edges for different operation types. Each node in the graph represents a specific operation or data element, allowing the system to analyze and process each operation type with tailored precision rather than treating all operations uniformly, thus reducing overall processing complexity.
Data Source
AI summary
A method includes receiving a permission request from a user to perform an operation in a computer environment. Data elements of operations previously performed by a plurality of users are received. A set of operation types are generated by identifying data elements of operations previously performed by other users of the plurality of users having operation types performed by the user. The data elements in the set are mapped into a graph database. Permission messages are generated with a correct response identified from a data attribute from a specific operation type previously performed by the user, and wrong responses identified from the specific operation type previously performed by the other users. An accumulated probability based on the permission respond message is computed using the graph database. The user is tagged based on the accumulated probability as a permissioned user for performing the operation, or a non-permissioned violator user.