SAT-BO: Verification Rule Learning and Optimization for FraudTransaction Detection

2025-07-03

AI Summary

Electronic payment platforms rely on manually crafted validation rules to detect anomalous transactions; however, such rules lack systematic robustness guarantees and are vulnerable to adversarial evasion, posing significant financial risks. This paper proposes the first automated framework integrating SAT solving with Bayesian optimization to formally model validation rules, uncover logical vulnerabilities, and iteratively enhance their attack resilience. Our approach synergizes formal verification, rule learning, and black-box optimization to enable defect-driven rule refinement. Evaluated on real-world payment data, the framework substantially improves rule coverage (+32.7%) and anomaly detection accuracy (+28.4%), while successfully identifying and patching multiple classes of stealthy evasion vulnerabilities. This work establishes a novel paradigm for provably secure risk-control rule design.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Safety and Robustness
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Electronic payment platforms are estimated to process billions oftransactions daily, with the cumulative value of these transactionspotentially reaching into the trillions. Even a minor error within thishigh-volume environment could precipitate substantial financiallosses. To mitigate this risk, manually constructed verification rules,developed by domain experts, are typically employed to identifyand scrutinize transactions in production environments. However,due to the absence of a systematic approach to ensure the robust-ness of these verification rules against vulnerabilities, they remainsusceptible to exploitation.To mitigate this risk, manually constructed verification rules, de-veloped by domain experts, are typically employed to identify andscrutinize transactions in production environments. However, dueto the absence of a systematic approach to ensure the robustness ofthese verification rules against vulnerabilities, they remain suscep-tible to exploitation. To ensure data security, database maintainersusually compose complex verification rules to check whether aquery/update request is valid. However, the rules written by ex-perts are usually imperfect, and malicious requests may bypassthese rules. As a result, the demand for identifying the defects ofthe rules systematically emerges.

Problem

• Detect fraud transactions in high-volume electronic payments
• Improve robustness of manually crafted verification rules
• Systematically identify defects in expert-written security rules

Innovation

• Automated verification rule learning for fraud detection
• Optimization of rules to prevent vulnerabilities
• Systematic defect identification in transaction rules