Risk Scoring Introduction
Last updated
Last updated
Overview The CUBE3.AI Risk Scoring Engine is a powerful tool for evaluating the risk associated with blockchain addresses, smart contracts, and transactions. It is available to integrate as a standalone product with a user interface (called Panorama), via API, or through data feeds. This engine delivers dynamic risk scores that clients can incorporate into their risk management workflows to identify and mitigate potential threats in real-time.
Risk Scores CUBE3.AI employs a combination of AI-driven analysis and heuristic evaluation to determine risk levels. Addresses and transactions are evaluated on a 1-100 scale, with the Risk Score representing a cumulative analysis of intent, patterns, and historical signals derived by our AI and ruleset — it’s not merely a confidence score. Use the following ranges to interpret risk scores:
• 0-30: Safe. Very unlikely to be malicious or have an illicit history.
• 31-69: Warning. Signals of malicious intent or history. Should be engaged with caution but not declined by default.
• 70-100: Unsafe. Very high likelihood of malicious intent or illicit history. Engage with utmost caution and consider declining by default.
Consider adjusting your risk parameters based on your business needs and risk tolerance. Consult with your CUBE3.AI representative for optimal settings.
Initial and Dynamic Analysis
Initial Analysis: a. Smart Contracts: We perform detailed code analysis, examining both Op and Byte code to detect malicious intent. This analysis is enhanced using pattern recognition and intent prediction, utilizing a combination of blockchain and web2 data. b. EOAs (Externally Owned Accounts): Risk assessment is conducted through advanced pattern recognition and intent prediction, leveraging both blockchain and web2 data to generate a probabilistic risk score.
Dynamic Scoring: a. Risk scores for EOAs and smart contracts are not static; they evolve over time based on ongoing transaction history, behavioral patterns, and new signals received. The scoring algorithm is designed to reflect the current risk level dynamically: i. Healing: Positive transaction behavior can reduce the risk score over time. ii. Sudden Increases: Detection of suspicious or malicious activities can cause a rapid increase in the risk score.
Transaction Scoring: a. Each transaction is evaluated holistically, incorporating risk insights from the involved EOAs and smart contracts, as well as the context of the transaction. If the transaction is completed, our system not only assigns a risk score but also provides detailed analysis, including the identification of any victims, attackers, and the flow of funds.
Detection Categories
Our Risk Scoring engine is designed to detect a broad range of threats across three primary categories:
Fraud: Detects deceptive activities, including romance scams, phishing fraud, token scams, ponzi schemes, and other fraudulent behaviors that aim to deceive users and misappropriate funds.
Cyber: Monitors EOAs and smart contracts for involvement in exploits or malicious intent.
Compliance: Identifies non-compliant EOAs and smart contracts, ensuring that interactions align with regulatory standards and avoiding entities that might pose a legal or reputational risk.
Your CUBE3.AI contact will provide a detailed list of threat categories detected by our models. , please contact us to discuss how quickly we can add support.
Example Use Case
Scenario: A financial institution integrates the CUBE3.AI Risk Scoring Engine to monitor and flag transactions based on risk levels.
Application: The institution sets up automated workflows to:
Reject transactions with a risk score above 69 (Unsafe).
Review and manually approve or reject transactions with a risk score between 31 and 69 (Warning).
Automatically approve transactions with a risk score below 30 (Safe).
Technical Notes:
The CUBE3.AI Risk Scoring Engine’s scores are dynamically generated in real-time, reflecting the most current risk assessment based on AI analysis and heuristic rules.
Clients are advised to periodically review and fine-tune their risk thresholds, ensuring alignment with evolving business strategies and regulatory requirements.
