External Account Authentication Using Activity Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to leverage data exchange between segregated user accounts for enhanced security measures, preventing the integration of security features across multiple accounts.
Innovation Solution
A system and method for authenticating external accounts using a machine learning model that analyzes overlap or correlation between user activity data from a secure account and external account content, generating a certainty level for pairing the accounts based on a threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users operate multiple accounts separately, then each account maintains its own security measures, but data from third party accounts cannot benefit security measures from the secure account
Solution Approach 1:
The patent merges data from multiple segregated accounts (secure account and external account) into a unified authentication process. The system combines user activity data from the secure account with external account content, allowing the machine learning model to analyze combined data patterns to verify account ownership, thereby improving security reliability through data integration.
Solution Approach 2:
The machine learning model acts as an intermediary between segregated account systems. It receives data from both the secure account and external account, processes this data through trained algorithms, and outputs an authentication determination. This intermediary component enables security verification across account boundaries without requiring direct system integration between the accounts themselves.
2Productivity
If traditional authentication methods are used, then account security is maintained, but processing time and resources increase due to lack of automated verification
Solution Approach 1:
The system implements self-service authentication where the machine learning model automatically processes user activity data and external account content to generate authentication determinations. The trained model independently evaluates whether accounts belong to the same user without requiring manual verification, thereby reducing processing time and resource consumption while maintaining security standards.
Solution Approach 2:
The machine learning model is pre-trained with authentication data and patterns before actual use. This preliminary training action enables the model to quickly and accurately determine account ownership relationships during authentication, reducing real-time processing time and resource requirements compared to traditional authentication methods.
Data Source
AI summary
Systems and methods for external account authentication are disclosed herein. They include receiving a call to pair the external account with a secure account, extracting external data from the external account, the external data corresponding to external account content, providing user activity data from the secure account as an input to an authentication machine learning model, providing the external data as an input to the authentication machine learning model, the authentication machine learning model configured to output a certainty level that the external account is associated with a user of the secure account based on the external data and the activity data, receiving the certainty level from the authentication machine learning model, determining that the certainty level meets a certainty threshold, and pairing the external account with the secure account based on determining that the certainty level meets the certainty threshold.