Evaluating the Potential of Quantum Machine Learning in Cybersecurity - A Case-Study on PCA-based Intrusion Detection Systems

Aug 4, 2026

Upload by Asher

Quantum computing is expected to change the limits of computation and to reshape cybersecurity, particularly through its effects on cryptography and the rise of quantum-enabled adversaries. At the same time, quantum scientists are designing quantum protocols and exploring quantum machine learning (QML) for defense. This work analyzes how QML could affect cybersecurity applications of traditional ML, studies potential quantum-computing advantages for cybersecurity-related learning tasks, and proposes a methodology to estimate the future impact of fault-tolerant QML algorithms. A case study applies the approach to PCA-based intrusion detection using standard datasets, identifying conditions for quantum advantage and highlighting needs for future quantum hardware and software improvements.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages32

Reading Time1 h 21 min

AccessFree to download

Introduction

Abstract

Keywords

Evaluating QML potential in cybersecurity

Quantum computing impact and post-quantum context

Methodology to quantify future QML impact

Case study: PCA-based network intrusion detection

Conditions for quantum advantage and future needs

Journal Pre-proof Evaluating the potential of quantum machine learning in cybersecurity: A case-study on PCA-based intrusion detection systems Armando Bellante, Tommaso Fioravanti, Michele Carminati, Stefano Zanero, Alessandro Luongo PII: S0167-4048(25)00030-6 DOI: [https://doi.org/10.1016/j.cose.2025.104341](https://doi.org/10.1016/j.cose.2025.104341) Reference: COSE 104341 To appear in: Computers & Security Received date : 15 February 2024 Revised date : 23 December 2024 Accepted date : 15 January 2025 Please cite this article as: A. Bellante, T. Fioravanti, M. Carminati et al., Evaluating the potential of quantum machine learning in cybersecurity: A case-study on PCA-based intrusion detection systems. Computers & Security (2025), doi: [https://doi.org/10.1016/j.cose.2025.104341](https://doi.org/10.1016/j.cose.2025.104341) . This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. © 2025 Published by Elsevier Ltd. Journal Pre-proof Evaluating the Potential of Quantum Machine Learning in Cybersecurity: A Case-Study on PCA-based Intrusion Detection Systems Armando Bellantea,1,∗, Tommaso Fioravantia,2 , Michele Carminatia,3 , Stefano Zaneroa,4 , Alessandro Luongob,c,5,∗ a Politecnico di Milano, Via Ponzio 34/5, 20133, Milano, Italia b Centre for Quantum Technologies, Block S15, 3 Science Drive 2, Singapore, 117543, Singapore cInveriant Pte. Ltd., 101 Cecil Street \#14-12, Singapore, 069533, Singapore Abstract Quantum computing promises to revolutionize our understanding of the limits of computation, and its implications in cryptography have long been evident. Today, cryptographers are actively devising postquantum solutions to counter the threats posed by quantum-enabled adversaries. Meanwhile, quantum scientists are innovating quantum protocols to empower defenders. However, the broader impact of quantum computing and quantum machine learning (QML) on other cybersecurity domains still needs to be explored. In this work, we investigate the potential impact of QML on cybersecurity applications of traditional ML. First, we explore the potential advantages of quantum computing in machine learning problems specifically related to cybersecurity. Then, we describe a methodology to quantify the future impact of fault-tolerant QML algorithms on real-world problems. As a case study, we apply our approach to standard methods and datasets in network intrusion detection, one of the most studied applications of machine learning in cybersecurity. Our results provide insight into the conditions for obtaining a quantum advantage and the need for future quantum hardware and software advancements. Keywords: Quantum computing, Quantum machine learning, QML, Evaluation, Framework, Impact, PCA, Principal Component Analysis, Network Intrusion Detection, Network Security 1. Introduction Quantum computing combines concepts from computer science, mathematics, and physics to provide a novel computational model. A quantum computer is a programmable physical system that obeys the laws of quantum physics. Writing code for a quantum computer means specifying the evolution of a quantum mechanical system such that the system’s final description encodes the output of the computation. Expected to expand the way we process information radically, quantum computing provides new primitives unavailable in classical information processing. ∗ Corresponding author [1](1 armando.bellante@polimi.it)[ armando.bel

FAQs

What problem does the paper study about quantum machine learning in cybersecurity?

It investigates the potential impact of quantum machine learning on cybersecurity applications that currently rely on traditional machine learning, especially for network intrusion detection.

How does the case study evaluate QML impact?

The paper applies its proposed methodology to standard methods and datasets used in network intrusion detection, focusing on PCA-based approaches.

What do the results indicate about achieving quantum advantage?

The results provide insight into the conditions needed to obtain a quantum advantage and outline the expected need for future quantum hardware and software advancements.

Aug 4, 2026

Upload by Asher