Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Proceedings of the AAAI Symposium Series

Hardware Robustness of Quantum Machine Learning Kernels for Malware Detection

Mary L. Cotrupi, Allison Aurilio, Sean Sanpietro, Fabiana Torres, Anwita Kasturi, Quinn Colognato, Brian Callahan

Published Nov 6, 2026• 0 citations
Publisher

Abstract

Quantum Machine Learning (QML) is beginning to show promise as an emerging technology for cybersecurity tasks. One such task is malware detection, which remains a difficult and critical problem for both individuals and today's organizations. While there is a growing literature on applying QML to malware analysis, many studies remain confined to simulators, leaving open the question of how simulation results translate to the Noisy Intermediate-Scale Quantum (NISQ) machines that exist today. In this paper, we compare quantum-kernel classification across four execution environments---exact statevector evaluation, ideal shot-based Qiskit Aer, noisy Aer, and the IBM Quantum System One housed at Rensselaer Polytechnic Institute---and include matched classical baselines. Our contributions are twofold: first, we benchmark the full pipeline on real NISQ hardware; second, we provide a reproducible case study quantifying how hardware noise affects quantum-kernel geometry and downstream classification accuracy. Although we do not demonstrate quantum advantage, hardware-minus-exact balanced accuracy remained within two percentage points under the tested conditions despite substantial kernel distortion for the wider circuits. This is evidence of empirical stability, not formal statistical equivalence. Feature compression using principal component analysis (PCA) substantially reduced hardware-induced kernel distortion, although its effect on predictive accuracy was dataset dependent. Our results provide a grounded benchmark for cybersecurity practitioners evaluating NISQ-ready QML pipelines.

DOI
10.1609/aaaiss.v10i1.43482

Related papers

Performance Analysis of Variational Quantum Classifier and Quantum Kernel SVM under NISQ Noise Models Using Qiskit Aer

Mahadevaswamy, Bhavaling Alias Pratima Khot, S. S. Ittannavar

The rapid advancement of Noisy Intermediate-Scale Quantum (NISQ) devices necessitates a systematic evaluation of quantum machine learning (QML) algorithms to determine their feasibility for near-term applications. This study aims to benchmark the Variational Quantum Classifier (VQC)and the Quantum Kernel Support Vector Machine (QSVM) under realistic noise conditions modeled using Qiskit Aer. The primary objective is to investigate the impact of depolarizing and amplitude damping noise on the classification performance of these algorithms. Using the Iris binary classification task, we simulated four noise levels (0, 0.01, 0.05, 0.1) and evaluated accuracy across 1024 measurement shots. Results show that QSVM achieves superior accuracy (70%) under ideal and lownoise conditions, while VQC exhibits higher resilience at moderate noise (50% at 0.05 noise level) due to its adaptive Variational parameters. At higher noise levels (0.1), both models converge to ~35–40% accuracy, indicating significant degradation. These findings provide actionable insights for algorithm selection on NISQ hardware, with VQC favored for moderately noisy devices and QSVM preferable for low-noise or error-mitigated systems. The study concludes by highlighting the need for noise-aware ansatz design and error mitigation techniques to enhance QML performance in NISQ regimes.

E3S Web of Conferences•Jan 1, 2026•0 citations

A short review of open-source malware datasets and their implications for quantum machine learning

Olatunde Yusuf Owolabi, Abdulrauph Olanrewaju Babatunde

The rapid development of quantum machine learning (QML) has created new opportunities for malware detection and classification. However, the effectiveness of QML-based malware research depends strongly on the availability and suitability of open-source malware datasets. Although many publicly accessible malware datasets have been designed for classical machine learning, their features and limitations have not been systematically scrutinised on quantum computing grounds. This short review provides a structured overview of publicly available open-source malware datasets: EMBER (Endgame Malware BEnchmark for Research), DREBIN Android malware dataset, CIC-MalMem-2022 (Canadian Institute for Cybersecurity Malware Memory Analysis Dataset 2022), and VirusShare, and evaluates their suitability for quantum machine learning applications. The datasets are analysed based on data modality, feature representation, mode of labelling, and accessibility. Key research issues are identified, including high dimensionality, class imbalance, uncertainty of labels, and dataset bias. Particular attention is given to limitations posed by near-term quantum devices, such as qubit availability, circuit depth restrictions, and data encoding overhead. Among the reviewed datasets, DREBIN offers the most favourable characteristics for near-term QML experimentation. Its sparse binary feature structure, after reduction to a 126-feature subset or via principal component analysis (PCA) to 15 - 50 components, yields compact vectors compatible with current qubit constraints. EMBER and VirusShare present the greatest encoding challenges owing to their very high dimensionality and lack of standardised feature representations. Angle encoding and hybrid quantum-classical approaches are identified as the most practical encoding strategies for current NISQ (Noisy Intermediate-Scale Quantum) devices. A five-criterion evaluation framework, covering feature dimensionality, encoding feasibility, dataset size, label quality, and preprocessing requirements, is proposed to guide dataset selection. The findings underscore the urgent need for purpose-built benchmark datasets designed with quantum hardware constraints in mind.

HO CHI MINH CITY OPEN UNIVERSITY JOURNAL OF SCIENCE - ENGINEERING AND TECHNOLOGY•Sep 10, 2026•0 citations

Assessing Claims of Advantage in Quantum Machine Learning: A Critical Review

Stefan Klug, Maximilian Moll

Abstract Quantum machine learning (QML) has attracted growing interest because quantum states and circuits may provide new representational primitives for learning, yet progress remains constrained by noisy intermediate-scale quantum (NISQ) hardware and heterogeneous evaluation practices. This article presents a critical review of recent QML architectures and representative empirical and theoretical studies, with emphasis on work published since 2022 alongside selected seminal references. To improve comparability, “quantum advantage” is assessed in three distinct senses: computational scaling under stated input-access assumptions, empirical predictive performance in the benchmark setting considered, and resource efficiency at a fixed budget accounting for both classical compute and quantum execution, including shot costs. Organized by architecture family and application domain, the review analyzes how baseline strength, hyperparameter optimization, preprocessing, and budget reporting shape conclusions. Overall, quantum feature maps and kernels, as well as variational (often hybrid) pipelines, can be competitive on selected small- to medium-scale benchmarks, but robust end-to-end evidence for a general practical advantage remains limited. Reported gains are often sensitive to budget matching and may be dominated by measurement overheads, dataset and preprocessing effects, and training instabilities. The review concludes that credible progress requires standardized benchmarking, transparent end-to-end resource accounting, and hardware-centered evaluations that test scalability and robustness beyond toy regimes.

•May 7, 2026•0 citations

Practical Evaluation of Quantum Kernel Methodsfor Radar Micro-Doppler Classification on Noisy Intermediate-Scale Quantum (NISQ) Hardware

Vikas Agnihotri, Jasleen Kaur Jasleen Kaur, Sarvagya Kaushik

Abstract This work presents an empirical study of a Quantum Support Vector Machine(QSVM) for classification of radar micro-Doppler signatures, used here as astructured benchmark for evaluating quantum kernel methods under realistichardware constraints. Extracted classical features are reduced using PrincipalComponent Analysis (PCA) to enable compact quantum encoding, and mappedinto a quantum kernel feature space through a fully entangling ZZFeatureMap.Classification is performed using a kernel-based QSVM and compared with aclassical SVM baseline under consistent preprocessing and evaluation conditions.Performance is assessed in both ideal simulation and on NISQ-era superconducting quantum processors, specifically IBM Torino (133-qubit) and IBM Fez(156-qubit). Results show that the QSVM attains competitive accuracy whileoperating on reduced feature dimensionality, with performance sensitivity tonoise, decoherence, and measurement shot count. Improved kernel stability isobserved on newer hardware architecture.The study does not claim quantumadvantage; instead, it provides a hardware-level evaluation of quantum kernelbehavior and clarifies current feasibility and limitations of QSVM approaches forstructured signal classification tasks.

•May 15, 2026•0 citations

Quantum Machine Learning for Cybersecurity Applications: Simulation and Hardware Validation

Zirui Zhu, Zisheng Chen, Xiangyang Li

Under tight feature and compute budgets, classical threat detection pipelines often degrade on near-decision-boundary events. Small quantum processors are now available, but existing work inadequately shows whether quantum components improve end-to-end threat detection under the above resource constrained conditions. This paper tries to address this gap with a hybrid architecture that uses a compact multilayer perceptron layer to compress the information in data and then routes the processed features to a few qubit quantum heads implemented in quantum support vector machine (QSVM) and variational quantum circuit (VQC) models. On a simulation platform, we benchmark these hybrid models against classical models with comparable parameter budgets on two representative cybersecurity tasks, network intrusion detection on NSL-KDD dataset and spam filtering on Ling-Spam dataset. To validate their precision on real quantum hardware, we deploy the best 4-qubit QSVM model on an IBM Quantum device with noise-aware execution, evaluated on a smaller sub-dataset. In the results, shallow quantum heads consistently match, and on difficult near-boundary cases modestly reduce missed attacks and false alarms compared to classical models using the same features. Hardware validation results track the simulation behavior closely enough that the remaining gap is dominated by device noise rather than model design. Furthermore, we conduct adversarial attacks to test the robustness of one QSVM model. Taken together, the study shows that even on small, noisy devices, carefully engineered quantum components may function as competitive, budget-aware components in practical cyber threat detection applications.

quant-pharXiv:2609.32911•Sep 29, 2026•0 citations

A Systematic Study of Noise Effects in Hybrid Quantum-Classical Machine Learning

Bhavna Bose, Muhammad Faryad

Near-term quantum machine learning (QML) models operate in environments wherein noise is unavoidable, arising from both imperfect classical data acquisition and the limitations of noisy intermediate-scale quantum (NISQ) hardware. Although most existing studies have focused primarily on quantum circuit noise in isolation, the combined influence of corrupted classical inputs and quantum hardware noise has received comparatively little attention. In this work, we present a systematic experimental study of the robustness of a variational quantum classifier under realistic multi-level noise conditions. Using the Titanic dataset as a benchmark, a range of dataset-level noise models-including speckle noise, impulse noise, quantization noise, and feature dropout are applied to classical features prior to quantum encoding using a ZZ feature map. In parallel, hardware-inspired quantum noise channels such as depolarizing noise, amplitude damping, phase damping, Pauli errors, and readout errors are incorporated at the circuit level using the Qiskit Aer simulator. The experimental results indicate that noise in classical input data can significantly intensify the effects of quantum decoherence, resulting in less stable training and noticeably lower classification accuracy. Together, these observations emphasize the importance of designing and evaluating quantum machine learning pipelines with noise in mind, and highlight the need to consider classical and quantum noise simultaneously when assessing QML performance in the NISQ era

quant-pharXiv:2604.11541•Apr 14, 2026•2 citations
Quantum Machine Learning (QML) is beginning to show promise as an emerging technology for cybersecurity tasks. One such task is malware detection, which remains a difficult and critical problem for both individuals and today's organizations. While there is a growing literature on applying QML to malware analysis, many studies remain confined to simulators, leaving open the question of how simulation results translate to the Noisy Intermediate-Scale Quantum (NISQ) machines that exist today. In this paper, we compare quantum-kernel classification across four execution environments---exact statevector evaluation, ideal shot-based Qiskit Aer, noisy Aer, and the IBM Quantum System One housed at Rensselaer Polytechnic Institute---and include matched classical baselines. Our contributions are twofold: first, we benchmark the full pipeline on real NISQ hardware; second, we provide a reproducible case study quantifying how hardware noise affects quantum-kernel geometry and downstream classification accuracy. Although we do not demonstrate quantum advantage, hardware-minus-exact balanced accuracy remained within two percentage points under the tested conditions despite substantial kernel distortion for the wider circuits. This is evidence of empirical stability, not formal statistical equivalence. Feature compression using principal component analysis (PCA) substantially reduced hardware-induced kernel distortion, although its effect on predictive accuracy was dataset dependent. Our results provide a grounded benchmark for cybersecurity practitioners evaluating NISQ-ready QML pipelines.
The rapid advancement of Noisy Intermediate-Scale Quantum (NISQ) devices necessitates a systematic evaluation of quantum machine learning (QML) algorithms to determine their feasibility for near-term applications. This study aims to benchmark the Variational Quantum Classifier (VQC)and the Quantum Kernel Support Vector Machine (QSVM) under realistic noise conditions modeled using Qiskit Aer. The primary objective is to investigate the impact of depolarizing and amplitude damping noise on the classification performance of these algorithms. Using the Iris binary classification task, we simulated four noise levels (0, 0.01, 0.05, 0.1) and evaluated accuracy across 1024 measurement shots. Results show that QSVM achieves superior accuracy (70%) under ideal and lownoise conditions, while VQC exhibits higher resilience at moderate noise (50% at 0.05 noise level) due to its adaptive Variational parameters. At higher noise levels (0.1), both models converge to ~35–40% accuracy, indicating significant degradation. These findings provide actionable insights for algorithm selection on NISQ hardware, with VQC favored for moderately noisy devices and QSVM preferable for low-noise or error-mitigated systems. The study concludes by highlighting the need for noise-aware ansatz design and error mitigation techniques to enhance QML performance in NISQ regimes.
The rapid development of quantum machine learning (QML) has created new opportunities for malware detection and classification. However, the effectiveness of QML-based malware research depends strongly on the availability and suitability of open-source malware datasets. Although many publicly accessible malware datasets have been designed for classical machine learning, their features and limitations have not been systematically scrutinised on quantum computing grounds. This short review provides a structured overview of publicly available open-source malware datasets: EMBER (Endgame Malware BEnchmark for Research), DREBIN Android malware dataset, CIC-MalMem-2022 (Canadian Institute for Cybersecurity Malware Memory Analysis Dataset 2022), and VirusShare, and evaluates their suitability for quantum machine learning applications. The datasets are analysed based on data modality, feature representation, mode of labelling, and accessibility. Key research issues are identified, including high dimensionality, class imbalance, uncertainty of labels, and dataset bias. Particular attention is given to limitations posed by near-term quantum devices, such as qubit availability, circuit depth restrictions, and data encoding overhead. Among the reviewed datasets, DREBIN offers the most favourable characteristics for near-term QML experimentation. Its sparse binary feature structure, after reduction to a 126-feature subset or via principal component analysis (PCA) to 15 - 50 components, yields compact vectors compatible with current qubit constraints. EMBER and VirusShare present the greatest encoding challenges owing to their very high dimensionality and lack of standardised feature representations. Angle encoding and hybrid quantum-classical approaches are identified as the most practical encoding strategies for current NISQ (Noisy Intermediate-Scale Quantum) devices. A five-criterion evaluation framework, covering feature dimensionality, encoding feasibility, dataset size, label quality, and preprocessing requirements, is proposed to guide dataset selection. The findings underscore the urgent need for purpose-built benchmark datasets designed with quantum hardware constraints in mind.
Abstract Quantum machine learning (QML) has attracted growing interest because quantum states and circuits may provide new representational primitives for learning, yet progress remains constrained by noisy intermediate-scale quantum (NISQ) hardware and heterogeneous evaluation practices. This article presents a critical review of recent QML architectures and representative empirical and theoretical studies, with emphasis on work published since 2022 alongside selected seminal references. To improve comparability, “quantum advantage” is assessed in three distinct senses: computational scaling under stated input-access assumptions, empirical predictive performance in the benchmark setting considered, and resource efficiency at a fixed budget accounting for both classical compute and quantum execution, including shot costs. Organized by architecture family and application domain, the review analyzes how baseline strength, hyperparameter optimization, preprocessing, and budget reporting shape conclusions. Overall, quantum feature maps and kernels, as well as variational (often hybrid) pipelines, can be competitive on selected small- to medium-scale benchmarks, but robust end-to-end evidence for a general practical advantage remains limited. Reported gains are often sensitive to budget matching and may be dominated by measurement overheads, dataset and preprocessing effects, and training instabilities. The review concludes that credible progress requires standardized benchmarking, transparent end-to-end resource accounting, and hardware-centered evaluations that test scalability and robustness beyond toy regimes.
Abstract This work presents an empirical study of a Quantum Support Vector Machine(QSVM) for classification of radar micro-Doppler signatures, used here as astructured benchmark for evaluating quantum kernel methods under realistichardware constraints. Extracted classical features are reduced using PrincipalComponent Analysis (PCA) to enable compact quantum encoding, and mappedinto a quantum kernel feature space through a fully entangling ZZFeatureMap.Classification is performed using a kernel-based QSVM and compared with aclassical SVM baseline under consistent preprocessing and evaluation conditions.Performance is assessed in both ideal simulation and on NISQ-era superconducting quantum processors, specifically IBM Torino (133-qubit) and IBM Fez(156-qubit). Results show that the QSVM attains competitive accuracy whileoperating on reduced feature dimensionality, with performance sensitivity tonoise, decoherence, and measurement shot count. Improved kernel stability isobserved on newer hardware architecture.The study does not claim quantumadvantage; instead, it provides a hardware-level evaluation of quantum kernelbehavior and clarifies current feasibility and limitations of QSVM approaches forstructured signal classification tasks.
Under tight feature and compute budgets, classical threat detection pipelines often degrade on near-decision-boundary events. Small quantum processors are now available, but existing work inadequately shows whether quantum components improve end-to-end threat detection under the above resource constrained conditions. This paper tries to address this gap with a hybrid architecture that uses a compact multilayer perceptron layer to compress the information in data and then routes the processed features to a few qubit quantum heads implemented in quantum support vector machine (QSVM) and variational quantum circuit (VQC) models. On a simulation platform, we benchmark these hybrid models against classical models with comparable parameter budgets on two representative cybersecurity tasks, network intrusion detection on NSL-KDD dataset and spam filtering on Ling-Spam dataset. To validate their precision on real quantum hardware, we deploy the best 4-qubit QSVM model on an IBM Quantum device with noise-aware execution, evaluated on a smaller sub-dataset. In the results, shallow quantum heads consistently match, and on difficult near-boundary cases modestly reduce missed attacks and false alarms compared to classical models using the same features. Hardware validation results track the simulation behavior closely enough that the remaining gap is dominated by device noise rather than model design. Furthermore, we conduct adversarial attacks to test the robustness of one QSVM model. Taken together, the study shows that even on small, noisy devices, carefully engineered quantum components may function as competitive, budget-aware components in practical cyber threat detection applications.
Near-term quantum machine learning (QML) models operate in environments wherein noise is unavoidable, arising from both imperfect classical data acquisition and the limitations of noisy intermediate-scale quantum (NISQ) hardware. Although most existing studies have focused primarily on quantum circuit noise in isolation, the combined influence of corrupted classical inputs and quantum hardware noise has received comparatively little attention. In this work, we present a systematic experimental study of the robustness of a variational quantum classifier under realistic multi-level noise conditions. Using the Titanic dataset as a benchmark, a range of dataset-level noise models-including speckle noise, impulse noise, quantization noise, and feature dropout are applied to classical features prior to quantum encoding using a ZZ feature map. In parallel, hardware-inspired quantum noise channels such as depolarizing noise, amplitude damping, phase damping, Pauli errors, and readout errors are incorporated at the circuit level using the Qiskit Aer simulator. The experimental results indicate that noise in classical input data can significantly intensify the effects of quantum decoherence, resulting in less stable training and noticeably lower classification accuracy. Together, these observations emphasize the importance of designing and evaluating quantum machine learning pipelines with noise in mind, and highlight the need to consider classical and quantum noise simultaneously when assessing QML performance in the NISQ era