Quantum-Neural Network Model for Platform Independent Ddos Attack Classification in Cyber Security

Abstract

Quantum Machine Learning (QML) leverages the transformative power of quantum computing to explore a broad range of applications, including optimization, data analysis, and complex problem-solving. Central to this study is the using of an innovative intrusion detection system leveraging QML models, with a preference for Quantum Neural Network (QNN) architectures for classification tasks. The inherent advantages of QNNs, notably their parallel processing capabilities facilitated by quantum computers and the exploitation of quantum superposition and parallelism, are elucidated. These attributes empower QNNs to execute certain classification tasks expediently and with heightened efficiency. Empirical validation is conducted through the deployment and testing of a QNN-based intrusion detection system, employing a subset of the CIC-DDoS 2019 dataset. Notably, despite employing a reduced feature set, the QNN-based system exhibits remarkable classification accuracy, achieving a commendable rate of 92.63%. Moreover, the study advocates for the utilization of quantum computing libraries such as Qiskit, facilitating QNN training on local machines or quantum simulators. The findings underscore the efficacy of a QNN-based intrusion detection system in attaining superior classification accuracy when confronted with large-scale training datasets. However, it is imperative to acknowledge the constraints imposed by the limited number of qubits available on local machines and simulators.