Quantum aware system detects romance scam conversations effectively
A Cognitive-Aware QML-CRL Framework for Detecting Affinity and Romance-Investment Fraud
Machine Learning
Summary
Romance scams trick people by manipulating their emotions over time. The authors designed a computer system that uses both quantum and classical computing to understand these tricky conversations better. It watches how certain biases appear as a chat goes on and decides when to raise an alarm. They tested this system using pretend chat examples, including tricky cases that look like scams but aren't, to see how well it works.
What this means in practice
- •For fraud detection teams: Use a hybrid quantum-classical model to identify romantic investment scams by tracking cognitive bias patterns during conversations.
- •For customer service teams: Spot manipulative sales pitches that mimic romance scams, helping to flag pushy or urgent but legitimate calls.
Tested on simulated data.
Authors
Bibhas Adhikari, Ramya Srinivasan
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.