AI Authentication Score Generation Using Geolocation Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in authenticating user verification requests effectively, particularly in preventing falsified requests and ensuring the legitimacy of access to machines or networks, as they lack robust mechanisms to verify the authenticity of the request itself independent of the user's identity.
Innovation Solution
The implementation of a system that uses artificial intelligence engines to generate and verify scores based on face images, device-specific noise patterns, and geolocation data, where a device captures a face image with a characteristic noise pattern and submits it along with geolocation data to a server machine for authentication, which then generates an authentication score to determine the legitimacy of the request.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional login credential verification is used, then user verification can be performed, but the system is vulnerable to falsified verification requests and unauthorized access
Solution Approach 1:
The authentication process is segmented into multiple independent verification components: device score generation (analyzing device characteristics and behavior), location score generation (verifying geolocation data), and face score generation (authenticating biometric data). Each component operates independently and contributes to the overall authentication decision, allowing the system to verify request authenticity without requiring a completely complex monolithic authentication system.
Solution Approach 2:
The patent introduces an intermediary authentication server that mediates between the client device and the protected resource. This server receives verification requests, generates multiple independent scores (device score, location score, face score), and combines them to produce an authentication decision. The intermediary handles the complexity of multi-factor verification while presenting a simple interface to both the user and the protected system.
2Reliability
If multiple authentication factors are used, then security and accuracy are enhanced, but the authentication process becomes more complex
Solution Approach 1:
The patent merges multiple authentication factors (device characteristics, geolocation data, biometric information) into a unified authentication process. The authentication server combines device score, location score, and face score through a weighted evaluation mechanism, presenting a single integrated authentication decision rather than requiring separate verification steps for each factor. This merging reduces the perceived complexity for users while maintaining high authentication accuracy.
Solution Approach 2:
The system dynamically adjusts the weightings of different authentication parameters (device score weight, location score weight, face score weight) based on risk assessment and contextual factors. This allows the authentication process to adapt its complexity - in low-risk scenarios, fewer factors may be heavily weighted, while high-risk scenarios trigger more rigorous multi-factor verification. The parameter changes enable flexible security levels without requiring a fixed complex process.
Data Source
AI summary
A machine trains an artificial intelligence engine to facilitate authentication of a request to verify a user. The machine accesses a reference set of obfuscated geolocations generated from actual geolocations from which a device submitted requests to verify the user. The machine groups the obfuscated geolocations into geographical clusters based on a predetermined cluster radius value and calculates a corresponding representative geolocation for each geographical cluster and a corresponding variance distance from the representative geolocation for each geographical cluster. The machine then generates a reference location score based on the representative geolocations of the geographical clusters and on the variance distances of the geographical clusters. The machine trains an artificial intelligence engine to output that reference location score in response to the reference set being input thereto. The trained artificial intelligence engine may then be provided to one or more devices.