Towards Quantum-Enhanced Machine Learning for Network Intrusion Detection
Arnaldo Gouveia, Miguel Correia
Abstract
Network Intrusion Detection Systems (NIDSs) are commonly used today to detect malicious activities. Quantum computers, despite not being practical yet, are becoming available for experimental purposes. We present the first approach for applying unsupervised Quantum Machine Learning (QML) in the context of network intrusion detection from the perspective of quantum information, based on the concept of quantum-assisted ML. We evaluate it using IBM QX in simulation mode and show that the accuracy of a Quantum-Assisted NIDS, based on our approach, can be high, rivaling with the the best conventional SVM results, with a dependence on the characteristics of the dataset.
Topics & Concepts
Intrusion detection systemComputer scienceQuantumContext (archaeology)IBMQuantum computerSupport vector machinePerspective (graphical)Artificial neural networkArtificial intelligenceQuantum machine learningMachine learningPhysicsQuantum mechanicsBiologyPaleontologyOpticsQuantum Computing Algorithms and ArchitectureNetwork Security and Intrusion DetectionQuantum Information and Cryptography