Quantum Preprocessing for Internet of Things Edge Computing Security Devices

Quantum preprocessing has the potential for significantly reducing computing power and storage space needed for tiny devices, such as Internet of Things devices, to satisfactorily operate as security devices such as an Intrusion Detection System. Specifically, we focus on Intrusion Detection Systems (IDS), which analyze network traffic to detect suspicious activities and potential security breaches. Traditional IDS implementations require substantial resources, making them difficult to deploy on edge devices. This paper proposes a quantum process to select critical features from the NSL-KDD dataset for IDS implementation. Our method leverages Grover’s algorithm combined with the Pearson correlation coefficient to identify the most relevant features for threat detection. The quantum algorithm executes feature selection through oracle creation and Grover diffusion processes, significantly reducing the dimensionality of the input data while preserving important security indicators. The selected features are evaluated based on quantum measurement results and domain specific security knowledge, considering quantum inaccuracy and hardware resource requirements. Our approach enables IoT devices to operate as effective IDS systems by avoiding the need to process the entire dataset during training, thereby optimizing efficiency and resource usage, further enabling the capability of resource constrained edge devices to operate robust IDS systems.