Q-SYNTH: Hybrid Quantum-Classical Adversarial Augmentation for Imbalanced Fraud Detection

2026-05-20

AI Summary

This study addresses the challenge of extreme class imbalance in credit card fraud detection, which typically biases models toward legitimate transactions and results in low recall and F1 scores for fraudulent cases. To mitigate this, the authors propose Q-SYNTH, a hybrid quantum-classical generative adversarial framework that, for the first time, employs a parameterized quantum circuit as the generator to synthesize minority-class fraud samples, paired with a classical neural network discriminator for adversarial training. The approach significantly reduces the marginal distribution discrepancy between generated and real data—as measured by Kolmogorov-Smirnov statistics and Wasserstein distance—while preserving downstream detection performance. This work demonstrates a favorable trade-off between distributional fidelity and classification efficacy, thereby validating the feasibility and potential of quantum-enhanced generative models for imbalanced classification tasks.

Abstract

Credit card fraud detection is fundamentally challenged by extreme class imbalance, where fraudulent transactions are rare yet operationally critical. This imbalance often biases supervised learners toward the legitimate class, leading to high overall accuracy but weaker fraud-class recall and F1-score. This paper introduces Q-SYNTH, a hybrid classical--quantum generative adversarial framework in which a parameterized quantum circuit serves as the generator and a classical neural network serves as the discriminator. Q-SYNTH is designed for minority-class fraud synthesis in tabular data and is evaluated along two dimensions: statistical fidelity to real fraud samples and downstream performance for fraud detection. To this end, generated samples are assessed using distributional similarity measures based on Kolmogorov-Smirnov statistics and Wasserstein distances, real-vs-synthetic detectability measured by AUC-ROC, and downstream classification performance across both quantum and classical classifiers. Under the reported protocol, Q-SYNTH reduces marginal distribution mismatch relative to a classical GAN baseline while maintaining competitive downstream fraud-detection performance. Although SMOTE achieves the strongest feature-wise similarity and the classical GAN attains the highest downstream performance in several settings, Q-SYNTH offers a favorable compromise between distributional fidelity and downstream performance, supporting the feasibility of hybrid quantum augmentation for imbalanced fraud detection.

Problem

• class imbalance
• fraud detection
• minority-class synthesis
• tabular data
• generative adversarial networks

Innovation

• quantum-classical hybrid
• generative adversarial network
• fraud detection
• class imbalance
• tabular data synthesis