Aurél Gábor Gábris, Ph.D.

Aurél Gábor Gábris, Ph.D.

Mgr. Martin Jureček, Ph.D.

Department of Information Security

This thesis explores the potential of quantum computing in enhancing malware classification through the application of Quantum Machine Learning (QML). The main objective is to investigate the performance of the Quantum Support Vector Machines (QSVM) algorithm compared to classical approaches for malware classification. A custom Python module was developed to select, extract, and preprocess malware samples from the publicly available PE Malware Machine Learning dataset. The QSVM algorithm, incorporating quantum kernels through different feature maps, was implemented and evaluated on a local simulator within the Qiskit SDK and on real quantum computers from IBM. Experimental results from simulators and quantum hardware provide insights into the behaviour and performance of quantum computers, especially in handling large-scale computations for malware classification tasks. This thesis lays the groundwork for future research in quantum-enhanced malware classification, exploring the feasibility and potential benefits of QML in advancing cybersecurity. The thesis summarizes the practical experience with using quantum hardware via the Qiskit interfaces. We describe in detail the encountered critical issues, as well as the fixes that had to be developed and applied to the base code of the the Qiskit Machine Learning library. These issues include missing transpilation of the circuits submitted to IBM Quantum systems and exceeding the maximum job size limit due to the submission of all the circuits in one job.

Thesis on DSpace