Enhancing Intrusion Detection Systems through Generative Dataset Balancing with Quantum Boltzmann Machines

We present an effective application of quantum machine learning in dataset balancing. This study explores the implementation of large Quantum Restricted Boltzmann Machines (QRBMs) which is a key advancement in Quantum Machine Learning (QML), as generative models on D-Wave's Advantage Machines to address dataset imbalance in Intrusion Detection Systems (IDS). The study leveraged Pegasus's enhanced connectivity and computational capabilities, with implementing a QRBM with 120 visible and 120 hidden units successfully with surpassing the limitations of current default embedding tools. As a result we observed that the QRBM synthesized over 1.6 million attack samples, achieving a balanced dataset of over 4.2 million records. We also present comparative evaluations with traditional balancing methods, such as SMOTE and RandomOversampler and observed that QRBMs produced higher-quality synthetic samples, significantly improving detection rates, precision, recall, and F\textsubscript{1} score across diverse classifiers. This study underscores the scalability and efficiency of QRBMs, completing balancing tasks in milliseconds. These findings highlight the transformative potential of QML and QRBMs as next-generation tools in data preprocessing, offering robust solutions for complex computational challenges in modern information systems.