Hybrid quantum–classical detectors are usually evaluated as monolithic alternatives to classical models, which conflates two separable questions: whether the hard cases can be identified, and whether a quantum model can resolve them. We introduce Q-RAD, a gated residual architecture that separates these questions by construction. A quantum-blind, quantum-cost-free gating function routes only ambiguous transactions to a financial-transaction-specific quantum-kernel branch, whose scores are fused residually with a classical trunk under an explicit finite-shot budget. We predeclare the architecture, an eight-comparison confirmatory family with Holm–Bonferroni correction, a cost metric in quantum circuit executions, and a refutation posture, then evaluate on the Kaggle Credit-Card Fraud dataset over ten repeated case-control splits under three blocking validity gates, including exact-equality replay of previously published results. The routing half of the architecture succeeds: the gate attains 0.889 AUROC against realized classical errors and captures 77% of them within a 22% routing budget. The quantum half fails: handed exactly those hard cases, the quantum residual produced zero net corrections in nine of ten seeds and one net regression in the tenth. Q-RAD attains mean case-control test F1 0.916 against 0.918 for the classical trunk and 0.922 for an otherwise identical classical second opinion; the hypotheses of improvement over the classical trunk, over random routing, and over a classical second opinion are all refuted after correction. We report this refutation as predeclared, and localise it: ambiguity in this task is identifiable from classical signals alone, but the quantum kernel cannot exploit that signal at any tested shot budget. Balanced-cohort metrics are benchmark values, not deployment-prevalence estimates.
Hybrid quantum–classical detectors are usually evaluated as monolithic alternatives to classical models, which conflates two separable questions: whether the hard cases can be identified, and whether a quantum model can resolve them. We introduce Q-RAD, a gated residual architecture that separates these questions by construction. A quantum-blind, quantum-cost-free gating function routes only ambiguous transactions to a financial-transaction-specific quantum-kernel branch, whose scores are fused residually with a classical trunk under an explicit finite-shot budget. We predeclare the architecture, an eight-comparison confirmatory family with Holm–Bonferroni correction, a cost metric in quantum circuit executions, and a refutation posture, then evaluate on the Kaggle Credit-Card Fraud dataset over ten repeated case-control splits under three blocking validity gates, including exact-equality replay of previously published results. The routing half of the architecture succeeds: the gate attains 0.889 AUROC against realized classical errors and captures 77% of them within a 22% routing budget. The quantum half fails: handed exactly those hard cases, the quantum residual produced zero net corrections in nine of ten seeds and one net regression in the tenth. Q-RAD attains mean case-control test F1 0.916 against 0.918 for the classical trunk and 0.922 for an otherwise identical classical second opinion; the hypotheses of improvement over the classical trunk, over random routing, and over a classical second opinion are all refuted after correction. We report this refutation as predeclared, and localise it: ambiguity in this task is identifiable from classical signals alone, but the quantum kernel cannot exploit that signal at any tested shot budget. Balanced-cohort metrics are benchmark values, not deployment-prevalence estimates.
Abstract—Hybrid quantum–classical detectors are usuallyevaluated as monolithic alternatives to classical models, whichconflates two separable questions: whether the hard cases can beidentified, and whether a quantum model can resolve them. Weintroduce Q-RAD, a gated residual architecture that separatesthese questions by construction. A quantum-blind, quantumcost-free gating function routes only ambiguous transactions toa financial-transaction-specific quantum-kernel branch, whosescores are fused residually with a classical trunk under anexplicit finite-shot budget. We predeclare the architecture, aneight-comparison confirmatory family with Holm–Bonferronicorrection, a cost metric in quantum circuit executions, anda refutation posture, then evaluate on the Kaggle Credit-CardFraud dataset over ten repeated case-control splits under threeblocking validity gates, including exact-equality replay of previouslypublished results. The routing half of the architecturesucceeds: the gate attains 0.889 AUROC against realized classicalerrors and captures 77% of them within a 22% routing budget.The quantum half fails: handed exactly those hard cases, thequantum residual produced zero net corrections in nine of tenseeds and one net regression in the tenth. Q-RAD attains meancase-control test F1 0.916 against 0.918 for the classical trunkand 0.922 for an otherwise identical classical second opinion; thehypotheses of improvement over the classical trunk, over randomrouting, and over a classical second opinion are all refuted aftercorrection. We report this refutation as predeclared, and localiseit: ambiguity in this task is identifiable from classical signalsalone, but the quantum kernel cannot exploit that signal atany tested shot budget. Balanced-cohort metrics are benchmarkvalues, not deployment-prevalence estimates.Keywords—Quantum Machine Learning; Quantum KernelMethods; Selective Prediction; Learning to Defer; HybridQuantum-Classical Models; Financial Fraud Detection; ShotNoise; Negative Results
This paper investigates whether hybrid quantum-classical machine learning can deliver practical improvements in financial fraud detection performance for card-based and other payment transactions. Building on a Guided Quantum Compressor architecture, the approach integrates an autoencoder, a variational quantum circuit, and a classical neural head, and then embeds this hybrid model into a mixture-of-experts framework including a state-of-the-art gradient-boosted tree classifier. Using a European credit card dataset with severe class imbalance, the routed hybrid architecture with 0.6 threshold achieves average precision scores of 0.793±0.085 compared to 0.770±0.096 of XGBoost on 3 repeated 5-fold cross-validation benchmarks. Precision and recall comparisons reveals a possible trade-off of fraud and nominal detections with a reduction in false positives at the cost of a small reduction in fraud detections. The improvements are achieved while adding only 7 to 21 minutes of extra inference time depending on the choice of hyperparameters. These results indicate that selectively routing transactions to quantum-classical models can enhance fraud detection while remaining compatible with the latency and operational constraints of modern financial institutions.
Coordinated financial fraud manifests as small, dense communities embedded in large transaction graphs. Isolating such a community is a combinatorial graph-partitioning problem of the kind often proposed for quantum optimisation, yet near-term quantum devices hold only tens of qubits while real graphs hold millions of accounts. We present scission, a hybrid pipeline built and evaluated under a design-science methodology, whose organising principle is that classical AI compresses the problem so a quantum solver can cut its combinatorial core. Classical anomaly scoring and a greedy reduction shrink the graph to a qubit-budget subgraph; a two-community modularity QUBO then isolates the ring, solved interchangeably by exact enumeration, simulated annealing, or a dependency-free statevector QAOA. We define an experimental protocol with explicit research questions, ground-truth metrics, and reproducibility controls. On a synthetic planted-ring benchmark (44 accounts reduced to 14 qubits) every backend attains the exact optimum, recovering all six ring members with one false positive (F1 = 0.923). We report no quantum advantage at feasible scale, formalise the pipeline's binding constraint as a reduction-recall bound, and give a structured research agenda toward real-data, real-hardware, and adversarial validation. We argue the contribution is architectural: a neutral QUBO interface behind which the solver improves as hardware matures, and an honest, reproducible account of where value does and does not yet arise.
Financial fraud detection remains difficult due to extreme class imbalance and subtle, nonlinear patterns in transactional data. We investigate a hybrid quantum–classical approach that couples a fidelity-based quantum kernel with a logistic regression classifier (QEKLR). A custom ZZ-inspired feature map comprising Hadamards, mixed-axis Ry/Rzencodings, tunable Ising-ZZ cross terms, and data re-uploading, embeds PCA-reduced, Min–Max scaled features into quantum states. The resulting fidelity kernel is evaluated and used within kernel logistic regression. Experiments on two benchmarks: BankSim (synthetic) and the European Credit Card Fraud dataset, use balanced subsets created via Random Under-Sampling. The proposed model attains the best performance on BankSim (AUC = 0.96; strongest F1), and is competitive on the credit-card dataset (AUC = 0.94), closely tracking XGBoost (AUC = 0.96) while outperforming logistic regression and a variational quantum classifier baseline. These results indicate that quantum kernel methods can provide practical gains on tabular fraud tasks while remaining aligned with current NISQ constraints. We also discuss the quadratic cost of exact kernel evaluation and outline scalable approximations for future deployment on larger, highly imbalanced datasets.
Classical ML models for fraud detection tend to break down on rare events, which are the cases that matter most. In imbalanced transaction datasets, new fraud patterns often fall outside what these models were trained to recognize. This paper presents a Hybrid Quantum-Classical Anomaly Detection Framework built to address that gap. Particle Swarm Optimization (PSO) handles feature selection, after which transaction features are encoded into quantum-inspired Hilbert spaces using Angle and Amplitude Encoding. Two quantum models, a Quantum Kernel SVM (QK-SVM) and a Variational Quantum Circuit (VQC), process these representations, and their outputs are fused with scores from Random Forest, XGBoost, and One-Class SVM through a weighted scoring scheme. On the Credit Card Fraud Detection benchmark, the hybrid framework outperforms classical-only baselines on rare event detection across Precision, Recall, F1-Score, and ROC-AUC, without needing actual quantum hardware.
Cyber fraud is still a serious threat to data-driven infrastructures, e-commerce sites, and financial systems. It frequently evades detection models that use static rules or traditional machine learning. In order to improve detection accuracy and cost sensitivity, A method is present Q-Defender Net, a hybrid quantum-classical framework that blends ensemble classification and quantum feature selection. After preprocessing the data with normalization and class balancing, the system maps feature into Hilbert space using quantum kernel alignment, and then uses QAOA to identify the most informative features. The parallel classifiers XGBoost and Quantum SVM then process these features, and their outputs are combined using weighted voting.High-value fraud cases are given priority by a cost-conscious loss function, which enhances practical impact. According to experimental results, Q-Defender Net outperforms FD4QC and Hybrid ML in terms of error rate and convergence speed, achieving 99% accuracy, 98% precision, and a 98.5% F1-score. It is a potent remedy for contemporary cybersecurity issues due to its modular, scalable architecture and adversarial robustness.