A Comparative Analysis of Classical and Quantum Machine Learning Models on Various Security Threats - UC-388 - Performance Comparison

Aug 4, 2026

Upload by Patrick

A comparative study evaluates classical machine learning models—neural networks, K-nearest neighbors, and support vector machines—against quantum counterparts for credit card fraud detection and related security threats. Using the Kaggle Credit Card Fraud Dataset, the analysis benchmarks each model’s ability to distinguish genuine and fraudulent transactions. Quantum circuit development leverages Python 3.10, Qiskit, and IBM Quantum Lab. Results show hybrid and quantum neural networks achieving strong accuracy, supporting further exploration of quantum approaches for secure, efficient fraud detection.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages1

Reading Time3 min

AccessFree to download

Performance Comparison

Objective

Framework Overview

Results and Discussion

Future Suggestions

Conclusions

A Comparative Analysis of Classical and Quantum Machine Learning Models on Various Security Threats Abstract UC-388 Performance Comparison Future Suggestions Cybersecurity has become an increasingly prevalent and sophisticated issue in the modern world, causing significant losses for individuals, businesses, and economies alike. The exponential growth of digital transactions has only accelerated the need for effective and efficient fraud detection systems to safeguard these financial ecosystems. Traditional machine learning techniques, such as Neural Networks (NNs), K-Nearest Neighbors (KNN), and Support Vector Machines (SVM), have played a crucial role in mitigating the impact of fraud by employing advanced algorithms to identify and prevent fraudulent transactions. With the recent advent of quantum computing and its potential to revolutionize the field of machine learning, there has been growing interest in exploring quantum algorithms for financial fraud detection. Quantum machine learning models are believed to offer significant computational advantages over their classical counterparts, which may lead to improved fraud detection capabilities. Objective This project aims to provide a comprehensive comparison of classical machine learning models, specifically NNs, KNN, and SVM, with their quantum counterparts in the context of credit card fraud detection. To demonstrate, we employ the widely-used Kaggle Credit Card Fraud Dataset, which contains a diverse set of anonymized transactional data labeled as genuine or fraudulent. Our comparative analysis focuses on assessing the performance of each model. By evaluating the strengths and limitations of both classical and quantum machine learning models, this study seeks to advance our understanding of the potential applications of quantum computing in financial fraud detection. Furthermore, the insights gained from this research will contribute to the development of more effective, secure, and efficient fraud detection systems, ultimately leading to a safer financial landscape for all stakeholders. Framework Overview The quantum circuits for the project were meticulously designed using Python 3 . 10 , the latest version of the widely-used programming language, in conjunction with IBM's Qiskit library. Qiskit is a comprehensive, open-source quantum computing framework that facilitates the development and execution of quantum algorithms. It provides various tools and functionalities to design, simulate, and optimize quantum circuits, making it an ideal choice for this project. To further streamline the execution of quantum circuits and harness the power of IBM's advanced quantum computing resources, the team also utilized IBM's Quantum Lab API. This cloud-based platform allowed for seamless integration and remote access to cutting-edge quantum hardware, enabling the execution of complex quantum algorithms with minimal latency. This combination of local development environments and cloud-based quantum computing resources ensured a highly efficient and productive development process for the project. The KNN results showed that the classical model achieved an 88% accuracy on classical data and 58% on quantum data, while the quantum model scored 58% and 61% on classical and quantum data, respectively. The Quantum Neural Network (QNN) achieved 92% accuracy on quantum data and 84% on classical data, while the Classical Neural Network reached 86% and 78% accuracy on quantum and classical data, respectively. The Hybrid Neural Network outperformed both with 94% accuracy on quantum data and 97% on classical data. In the SVM results, the classical model scored 86% on classical data and 52% on quantum data, while the quantum model scored 34% and 38% on classical and quantum data, respectively. Overall, the Hybrid Neural Network provided the best performance balance among the compared models. Figure 1 . Performance Comparison Between Classical and Quantum KNN Figure 2

FAQs

What is the objective of UC-388 in the study?

To compare classical machine learning models (NN, KNN, SVM) with quantum machine learning models for credit card fraud detection, focusing on performance differences.

Which dataset is used for the credit card fraud comparison?

The study uses the Kaggle Credit Card Fraud Dataset containing anonymized transactions labeled as genuine or fraudulent.

How are the quantum circuits implemented and executed?

Quantum circuits are designed using Python 3.10 and IBM’s Qiskit, with IBM Quantum Lab API used for streamlined execution on remote quantum hardware.

What overall model performs best in the reported results?

The Hybrid Neural Network provides the best overall performance balance, achieving 94% accuracy on quantum data and 97% on classical data.

Aug 4, 2026

Upload by Patrick