A Cognitive-Aware QML-CRL Framework for Detecting Affinity and Romance-Investment Fraud

2026-10-06

AI Summary

This study addresses the challenging problem of detecting "Pig Butchering" romance-investment fraud that exploits cognitive biases. To this end, it proposes a hybrid quantum-classical framework that pioneers the mapping of cognitive biases and temporal narratives onto parameterized quantum circuits. Specifically, conversational features are modeled through quantum entanglement layers and integrated with a reinforcement learning agent grounded in optimal stopping theory to dynamically identify fraudulent behavior. This work contributes a novel cross-disciplinary integration of cognitive psychological mechanisms and quantum machine learning. Evaluated on a synthetic dialogue dataset containing hard negative samples, the proposed approach effectively identifies deceptive patterns, offering a new paradigm for the intelligent detection of complex social engineering attacks.

Abstract

We present a hybrid quantum-classical framework that detects affinity and romance-investment fraud by modelling the cognitive biases in a manipulative conversation. In our proposed framework, cognitive biases central to this fraud class are carried by dedicated qubits in a structured parameterized quantum circuit, together with a frame qubit makes the encoding sensitive to the temporal order of manipulative reframing, and a narrative qubit that aggregates co-occurrence through a trainable entanglement layer. The circuit parameters are trained jointly with a classical reinforcement-learning agent that decides, turn by turn, whether to flag the conversation, modeled as an optimal stopping problem. We evaluate the model's performance on synthetic conversations that include hard negatives, legitimate but urgent, and legitimate but pushy sales conversations.

Problem

• affinity fraud
• romance-investment fraud
• cognitive bias detection
• fraud detection
• manipulative conversation

Innovation

• Quantum Machine Learning
• Cognitive Bias Modeling
• Parameterized Quantum Circuit
• Reinforcement Learning
• Optimal Stopping