LATIDIA · Ciberseguridad

SR-Fraud: un marco de agente LLM reflexivo supervisado por resultados para la detección de fraude de pagos no estacionarios

arXiv: 2609.27287v1Tipo de anuncio: cross Resumen: La detección de fraude de pago en tiempo real es un problema de predicción de transmisión no estacionaria: los adversarios se adaptan antes de que maduren las etiquetas supervisadas y los ataques de ráfaga localizados pueden advertir

La noticia

arXiv:2609.27287v1 Announce Type: cross Abstract: Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized burst attacks can cause losses before retraining. Production systems typically rely on tabular classifiers and rules, which can struggle to capture these emerging sequential patterns before periodic retraining occurs. We present SR-Fraud, an outcome-supervised reflective LLM framework that decouples request-time decisions from offline adaptation. A frozen, stateless agent scores each transaction from a Hybrid Episodic Window to track behavioral shifts, while an offline reflection agent proposes boundary hypotheses from matured errors. A deterministic verifier then admits only supported hypotheses into an executable knowledge state. On a production