Sensor Signal Malicious Data Binary Classification: A Comparison of QNN, and VQC

The importance of cyber security postures in various information technology (IT) or operations technology (OT) environments cannot be overstated, considering the significance of the cyber-physical system. The escalating risks in the intricate realm of cyberspace must be immediately evaluated, given their potential to inflict significant harm. Although machine learning has made significant progress to date, it is crucial to acknowledge that future cyberattacks will likely become more sophisticated. In this context, quantum machine learning is a clear and logical choice for the future. However, are available resources ideally open-source sufficient enough for finding a trade-off between the accuracy and computation time is a curious query worth contemplating. Size of the dataset is also another factor to include in the wondering space. This research aims to evaluate and compare several quantum supervised classification techniques with a conventional traditional method for binary classification of a dataset containing harmful sensor data.