Graph Attention Network for Virtual Asset Wallet Risk Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current virtual asset exchanges lack the means to prevent illegal transactions or misuse of virtual asset wallets, as there is no established standard for determining the risk level of virtual asset wallets.
Innovation Solution
A system and method using a graph attention network (GAT) to generate a virtual asset wallet address blacklist database, which includes a GAT AI engine server that trains a GAT-based AI model using pre-stored data from index, transaction, and blacklist databases to calculate GAT scores and estimate high-risk wallet addresses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a GAT-based AI model is trained to calculate risk scores for virtual asset wallets, then the accuracy of identifying high-risk wallets is improved, but the complexity of the system increases
Solution Approach 1:
The system is divided into multiple specialized servers: an index database server for storing wallet data, a virtual asset transaction analysis database server for transaction records, a main blacklist server for known malicious addresses, and a GAT AI engine server for risk calculation. This segmentation allows each component to focus on a specific function, improving overall system accuracy while managing complexity through modular architecture.
Solution Approach 2:
The GAT AI engine server acts as an intermediary between the stored data and the risk assessment process. It receives data from multiple sources, processes it through the trained AI model, and generates risk scores that can be used by external systems. This intermediary layer simplifies the interface for users while encapsulating the complex AI processing internally.
2Reliability
If comprehensive transaction data is collected and analyzed using GAT learning, then the reliability of risk estimation is improved, but the loss of time for data processing increases
Solution Approach 1:
The system performs preliminary actions by pre-storing comprehensive transaction data, wallet indices, and known blacklist information in optimized database structures before risk assessment is needed. The GAT AI model is trained in advance on historical data, so when actual risk assessment is required, the system can quickly query and process new transactions using the pre-established models and data structures, reducing real-time processing time while maintaining high reliability.
3Reliability
If a blacklist database is generated and maintained for high-risk wallets, then the ability to prevent fraudulent transactions is improved, but the device complexity for maintaining and updating the blacklist increases
Solution Approach 1:
The system implements feedback mechanisms where the GAT AI engine continuously analyzes new transactions and updates risk assessments. The blacklist is dynamically maintained based on feedback from the AI model's risk score calculations and actual fraudulent transaction outcomes. This feedback loop allows the system to automatically update and refine the blacklist without manual intervention, improving fraud prevention capability while reducing the operational complexity of maintenance.
Data Source
AI summary
A system and method for generating a virtual asset wallet address blacklist database based on a graph attention network (GAT) are disclosed. A GAT AI engine server is configured to train a GAT-based AI model using an index of a full node for each virtual asset pre-stored in an index database server, common transaction item information pre-stored in a virtual asset transaction analysis database server, and a main blacklist consisting of high-risk virtual asset wallet addresses pre-stored in a main blacklist server, to calculate GAT scores based on the trained AI model, to estimate high-risk virtual asset wallet addresses using the calculated GAT scores, and to generate a GAT blacklist consisting of the estimated high-risk virtual asset wallet addresses; and a GAT blacklist database server is configured to store the GAT blacklists generated by the GAT AI engine server.