Graph-Based Synthetic Identity Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems are ineffective in detecting synthetic identities linked to fraud-facilitating accounts, as they fail to identify deviations in expected electronic relationships between primary and secondary entities, leading to unauthorized access and fraudulent activities in interactive computing environments.
Innovation Solution
The implementation of graph-based techniques to analyze account and transaction data, identifying clique graph communities and comparing them to known patterns to detect synthetic identities, providing real-time fraud warnings before completing transactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional identity verification methods are used, then the simplicity of online transactions is maintained, but synthetic identities can easily create fake accounts without detection
Solution Approach 1:
The patent transitions from traditional single-entity verification to multi-dimensional graph-based analysis. By representing users, devices, and transactions as nodes and relationships as edges in a graph structure, the system adds dimensional depth to identity verification, enabling detection of synthetic identities through relational patterns rather than isolated attribute checking
Solution Approach 2:
The system performs preliminary graph construction and community detection before actual transactions occur. By pre-building the graph database with user relationships and pre-identifying suspicious community patterns, the system prepares detection capabilities in advance, allowing rapid verification during transactions without real-time computational overhead
2Reliability
If graph-based community detection is implemented, then synthetic identities linked to fraud-facilitating accounts are detected, but computational complexity and processing time increase
Solution Approach 1:
The system performs graph construction, community detection, and suspicious pattern identification in advance before transactions occur. By pre-processing the graph data and storing community structures, the system avoids performing computationally intensive operations during real-time transactions, thus maintaining both high detection accuracy and fast processing speed
Solution Approach 2:
The patent divides the large-scale graph into smaller community subgraphs based on relational proximity. By segmenting the graph into manageable communities and analyzing them independently, the system reduces computational complexity while maintaining detection accuracy, as fraud patterns typically manifest within localized communities rather than across the entire graph
3Measurement precision
If comprehensive relationship analysis is performed, then deviations in expected electronic relationships are identified, but data processing requirements and system resources increase
Solution Approach 1:
The patent applies different analysis depths to different parts of the graph based on local characteristics. By identifying communities with varying degrees of suspiciousness and applying targeted analysis only to high-risk communities, the system achieves high detection precision while minimizing overall data processing volume, rather than uniformly analyzing all relationships
Data Source
AI summary
In some aspects, a computing system is configured to use graph-based techniques to detect synthetic identities. The computing system can generate a collection of graphs based on account data and transaction data for online entities. The collection of graphs includes multiple graph communities, each graph community including nodes and edges. Each node represents a user and an edge between a first node and a second node indicates a user represented by the second node is an authorized user of the user represented by the first node. The computing system can identify a clique graph community in the collection of graphs and compare the identified clique graph community with a known clique graph community that includes synthetic identities. The computing system can determine nodes in the identified clique graph community to be synthetic identities based on determining that the identified clique graph community is equivalent to the known clique graph community.