Citation

Rezaei, Paria and Rahgozar, Behnaz and Khan, Mohammad Shadab and Yadollahi, Mehdi and SaberiKamarposhti, Morteza (2026) Quantum Machine Learning for Cyber Threat Intelligence: A Scoping Review of Current Capabilities and Future Directions. In: 22nd IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2026, 1 May 2026 - 2 May 2026, Kuala Lumpur, Malaysia.

Text 21.pdf - Published Version Restricted to Repository staff only Download (308kB)

Abstract

Emerging cyber threats demand novel detection and analysis paradigms that classical machine learning approaches are increasingly unable to address at requisite scale and speed. Quantum Machine Learning (QML), leveraging quantum mechanical phenomena such as superposition and entanglement, has emerged as a promising framework for cyber threat intelligence (CTI). This scoping review systematically examines 24 published works from 2020 to 2025 following the PRISMA-ScR protocol. We classify QML frameworks like Quantum Support Vector Machines (QSVM), Quantum Neural Networks (QNN), Variational Quantum Circuits (VQC), and Quantum Convolutional Neural Networks (QCNN) across four primary CTI domains: intrusion detection, malware classification, anomaly detection, and phishing detection. Results show that QML models achieved up to 98% accuracy in intrusion detection and 97% in IoT anomaly detection on curated benchmark datasets. Critical caveats apply: 83.3% of studies relied exclusively on quantum simulators rather than real hardware, most benchmarks used datasets predating 2017, and the classical pre-processing and post-processing overheads in hybrid architectures substantially qualify reported speedup claims. We assess hardware constraints in Noisy Intermediate-Scale Quantum (NISQ) devices, data encoding bottlenecks, and missing quality benchmarks. NIST post-quantum cryptography standards (FIPS 203–205, August 2024) and IBM quantum hardware milestones are discussed as contextual anchors. A structured research agenda concludes the review.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Quantum machine learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	01 Jul 2026 07:00
Last Modified:	01 Jul 2026 07:00
URII:	http://shdl.mmu.edu.my/id/eprint/16183

Downloads

Edit (login required)