Identity Network for Synthetic Identity Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to effectively identify synthetic identities, which are combinations of real and fictitious attributes, making it difficult for relying parties to distinguish them from valid identities, especially in network communications, leading to potential fraud.
Innovation Solution
A system and method that utilize an identity network to generate an assessment metric based on scores from stolen identity listings, fraud patterns, and collusive relationships, and attribute commonality analysis to determine the likelihood of a synthetic identity, thereby providing a risk score for relying parties to assess and verify identities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional identity verification methods are used, then verification process is simple, but synthetic identities cannot be effectively identified
Solution Approach 1:
The verification system is segmented into multiple independent scoring engines (early detection score, profile score, collusion score) that each evaluate different aspects of identity risk. This allows the complex verification task to be divided into manageable components while achieving comprehensive synthetic identity detection
Solution Approach 2:
The identity network serves multiple functions: it stores stolen identity data, analyzes fraud patterns, evaluates collusion relationships, and generates comprehensive risk scores. This multi-functional approach enables a single system to handle diverse verification requirements without requiring separate specialized systems
2Reliability
If comprehensive fraud detection analysis is performed, then synthetic identity identification improves, but processing time increases
Solution Approach 1:
The system pre-calculates and stores stolen identity listings, fraud patterns, and collusion relationships in the identity network before verification is needed. During actual verification, these pre-prepared data structures enable rapid scoring without requiring real-time computation of complex fraud patterns
Solution Approach 2:
The system continuously updates the identity network with new fraud patterns and stolen identity data based on verified fraud cases. This feedback loop improves detection reliability over time while the updated patterns are efficiently stored and reused in subsequent verifications
Data Source
AI summary
Systems and methods are provided for use in identifying synthetic party identities. One exemplary method includes receiving, at a computing device, a request from a relying party to assess validity of an identity presented by an asserting party in a network communication between the asserting party and the relying party, where the request includes identity data associated with the identity of the asserting party. The method also includes calculating, by the computing device, an assessment metric representative of the validity of the identity of the asserting party, where the assessment metric is based on at least one score derived from the identity data, and transmitting, by the computing device, the assessment metric to the relying party, whereby the relying party utilizes the assessment metric to determine whether or not to further interact with the asserting party in connection with the network communication.