The increasing needs in data sharing in the fields of finance, governance, and artificial intelligence pose a major threat to privacy, particularly in quantum computing. In this paper, a hybrid privacy-preserving system incorporating simulated BB84 Quantum Key Distribution (QKD) to generate secure keys, reversible pseudonymization with encrypted mapping vaults, automatic key rotation, and re-identification risk analysis by machine learning are introduced. Also, optional differential privacy layer allows irreversible anonymization in the cases of analysis. The proposed system will enable two modes, that is, recovery of secure data and the ability to publish data in privacy modes. The experimental findings indicate that authorized users have 100% recovery accuracy, re-identification risk is low and is close to random guessing and data utility is acceptable given the privacy restrictions. FastAPI and Streamlit are used to implement the framework, which is appropriate in the real-world deployment in clouds.
Srividhya Ganesan, G. Vijayasekaran, Sujith R· 2026 4th International Confe...· 0 citations
Credit card fraud detection remains a challenging binary classification problem because fraudulent transactions are rare, transaction patterns are complex, and false negatives may have important operational consequences. This study presents a Hybrid Classical–Quantum-Inspired Neural Network (HCQNN) with a simulated variational quantum circuit for credit card fraud detection. The proposed framework combines classical preprocessing, SMOTE-based class balancing, neural network-based feature learning, and quantum-inspired variational feature transformation. The model was evaluated using the Credit Card Fraud Detection dataset after applying SMOTE to the training data and was compared with three classical baseline classifiers: Logistic Regression, Decision Tree, and Linear Support Vector Machine. The experimental results show that the proposed HCQNN achieved an AUC of 97.85%, precision of 91.20%, recall of 90.10%, and an F1-score of 90.64%. These values indicate improved classification balance, particularly in the detection of minority-class fraud cases, compared with the selected baseline models. Training and validation behaviour also showed stable convergence, with training and validation accuracies exceeding 96% and 95%, respectively. Since the variational quantum circuit was simulated on classical hardware, the findings should be interpreted as evidence of the value of hybrid feature learning and quantum-inspired transformations rather than as proof of quantum computational advantage. The study provides a basis for further evaluation using broader datasets, additional baseline models, and real quantum hardware.
V. Srividhya, Srividhya Ganesan· Asian Journal of Research in...· 0 citations