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

International Journal of Academic and Industrial Research Innovations(IJAIRI)

QML for Edge Anomaly Detection: Variational Circuits on MQTT/NS-3 Stream

Murali Krishna Pasupuleti

Published Dec 30, 2023• 21 citations
Publisher

Abstract

Abstract Edge anomaly detection in telemetry streams is constrained by tight energy budgets, fluctuating connectivity, and limited compute. This study evaluates quantum machine learning (QML) for such settings by integrating variational quantum circuits with an MQTT ingestion layer and an NS-3 network emulator. The approach combines hardware-efficient and QAOA-style ansätze with angle and amplitude encodings; stochastic gradient updates are performed via SPSA with measurement-shot scheduling tuned to network conditions. Methods include closed-loop simulation of packet loss, jitter, and delay across MQTT QoS tiers, followed by deployment-style inference profiling under device power caps. On synthetic yet representative workloads, the proposed QML detectors achieve competitive F1 relative to compact classical baselines (Δ≤3 percentage points), reduce energy per inference by 20–35% at matched accuracy, and meet p99 end-to-end latency targets under 40–45 ms for QoS-1/2 paths. Implications include a viable path to power-aware detection on constrained runtimes; limitations concern shot noise, small qubit counts, and transferability from simulation to hardware backends. Why it matters: coupling network-aware simulation with QML clarifies when variational circuits are Pareto-efficient on the edge. What’s inside: an MQTT/NS-3 harness, circuit/encoding recipes, training and calibration procedures, ablation studies on QoS and impairments, and deployment-oriented metrics (F1, energy/inference, p95/p99 latency). Keywords quantum machine learning, variational quantum circuits, hardware-efficient ansatz, QAOA, angle encoding, amplitude encoding, SPSA, MQTT, NS-3, edge anomaly detection, energy efficiency, latency profiling

DOI
10.62311/nesx/rp-301223-174-188

Related papers

Advancements In Quantum Machine Learning: Bridging Quantum Computing And Artificial Intelligence

Yichen Zhao

Quantum Machine Learning (QML) unites quantum computing with modern AI to achieve potential gains in expressivity, runtime, and sample efficiency. This paper synthesizes advances in quantum feature maps, variational quantum circuits (VQCs), and hybrid quantum-classical workflows deployable on noisy intermediate-scale quantum (NISQ) hardware. We outline design principles for data encoding, ansatz selection, and trainability, and summarize error-aware practices—error mitigation, shot-frugal estimation, and compiler co-design. Using synthetic but instructive experiments, we illustrate scaling behavior, noise sensitivity, end-to-end inference latency across backends, and optimizer convergence in variational training. We conclude with an agenda emphasizing domain-aligned encodings, rigorous benchmarking, and reproducible open science to validate advantage beyond asymptotic claims.

Computer Science Bulletin•Dec 31, 2025•0 citations

Variational Quantum Models

Hamid D. Ismail

This chapter develops variational quantum models as the dominant framework for near-term quantum machine learning (QML), emphasizing their role as trainable quantum circuits embedded within hybrid quantum-classical optimization loops. Building on earlier chapters on encoding and quantum feature geometry, it formulates parameterized quantum circuits (PQCs) as families of unitary transformations acting on reference states, with model outputs obtained through expectation values of observables. This measurement-based structure makes variational learning inherently stochastic and closely ties model behavior to circuit architecture, observable choice, and optimization strategy. This chapter examines variational quantum circuits (VQCs) as learning models, introduces quantum neural networks (QNNs) as structured variational architectures, and analyzes layered, data-reuploading, recurrent, and hybrid classical-quantum designs. It highlights the central tension between expressivity and trainability, showing how universality and approximation power are counterbalanced by optimization barriers such as barren plateaus. The discussion further develops ansatz design strategies, supervised, fidelity-based, and energy-based losses, regularization under noise, and practical methods for gradient estimation and optimization, including the parameter-shift rule, Simultaneous Perturbation Stochastic Approximation (SPSA), and layer-wise training. Together, these ideas establish variational quantum models as a flexible yet hardware-constrained paradigm whose practical success depends on careful coordination among architecture, measurement, and optimization.

CRC Press eBooks•Nov 4, 2026•0 citations

Noise-Aware QML: Adaptive Noise-Regularized Variational Quantum Circuits for Parameter-Efficient Tabular Anomaly Detection

Saksham Garg, Dhruti A, Panchadip Bhattacharjee +3 more

Anomaly detection on high-dimensional tabular data requires models that are simultaneously compact, robust to noise, and interpretable, which are not met well by traditional ensemble learning approaches under strict parameter budgets. This work introduces NoiseAware-QML, a Variational Quantum Circuit (VQC) approach that incorporates a learnable noise parameter$\sigma$directly into the quantum ansatz, allowing the circuit to adaptively learn noise robustness during optimization through the reparameterization trick. The proposed 4-qubit, 4-layer VQC requires only 54 trainable parameters, a$715 \times$reduction over Random Forest and$91 \times$reduction over XGBoost, while maintaining a multi-seed mean ROC-AUC of$0.8366 \pm 0.0083$(95% CI: [0.8252, 0.8446]) on UNSW-NB15. Three robustness advantages with respect to parameter budget are formally established: (i) robustness to noise-1.84% AUC loss at$\sigma=0.10$compared to 4.12% for Random Forest (2.24× better) and 2.41% for a comparable-sized Dropout-MLP$(1.31 \times$better); (ii) calibration-$\mathbf{E C E}=0.0726$, improving over Random Forest (0.1127) and MLP (0.1151) by 36-37% without calibration correction; (iii) cross-dataset stability-only 5.36% AUC loss on NSL-KDD compared to 8.47% for Random Forest. Ablation study over three seeds verifies that adaptive noise regularization always improves over all variants by$\approx 0.089$AUC. Explainability through quantum-native means, per-gate gradientnorm heatmaps, and Bloch sphere analysis, demonstrates that the second-highest PCA variance component is actually harmful to anomaly detection, a result hidden from classical feature selection. Simulation-based deployment analysis confirms that the model generalizes to simulated NISQ hardware settings with AUC degradation of less than 2%.

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)•Jul 1, 2026•0 citations

Hybrid Quantum–Classical Models for Forecasting and Anomaly Detection on Edge IoT Devices

Rayen Hajjem, Akramul Azim, Moncef Triki

The growing complexity of Internet of Things (IoT) networks has generated massive multivariate time-series data at the edge, challenging traditional forecasting and anomaly-detection models due to limited computation, memory, and energy on edge devices. Quantum machine learning (QML) provides a promising solution through expressive, parameter-efficient models that align with these constraints. This study proposes two distinct quantum-classical approaches for edge-based IoT analytics. The first combines a Quantum Neural Network (QNN) with a Quantum Autoencoder (QAE) to deliver lightweight forecasting and anomaly detection. The second employs Quantum Long Short-Term Memory (QLSTM) networks, exploring multiple variants and introducing optimization strategies to enable efficient deployment on a Raspberry Pi 5 using PennyLane simulators. Both approaches are evaluated on two real-world IoT datasets Bker (weather parameters) and ETTm1 (transformer temperature) and with a unified preprocessing pipeline incorporating normalization and PCA-based dimensionality reduction. Results show that QLSTM variants achieve superior forecasting accuracy, while QNN+QAE ensures robust anomaly detection with minimal resource overhead. A lightweight QLSTM variant strikes the best balance between accuracy and inference latency, enabling real-time edge deployment. To our knowledge, this is among the first practical demonstrations of QML-based forecasting and anomaly detection directly on edge hardware, highlighting a feasible pathway toward quantum-enhanced IoT intelligence.

International Conference on Sciences and Techniques of Automatic Control and Computer Engineering•Dec 20, 2025•1 citation

Quantum Anomaly Detection in network traffic using Variational Quantum Classifiers

Mir H M Ilham, Hardique Dasore, Abdulrahman Ababneh +5 more

The increasingly complex cybersecurity landscape requires more advanced network anomaly detection systems. Although, classical machine learning models are known to be effective, they reach computational bottlenecks when processing high-dimensional data. This study investigates the potential of Quantum Machine Learning (QML) for network traffic anomaly detection by evaluating four distinct Variational Quantum Classifier (VQC) architectures. A synthetic network traffic dataset is generated for the evaluations. The VQC models systematically varied feature encoding methods, parameterized ansatz circuits, quantum neural network types, and classical optimizers. Experimental results show that a trade-off exists between circuit expressivity and optimization stability. Deeper circuits (VQC-4) achieved higher accuracy of upto 89.0\%, while simultaneously being sensitive to training conditions. A shallower variant (VQC-1) under performed, although it had consistent and stable optimization curves. Class-dependent biases were also observed such as in VQC-2, where the model struggled to find an effective decision boundary, and produced a large number of false negatives. The best performing model in this study (VQC-3) combined ZFeatureMap with RealAmplitudes ansatz, optimized using ADAM. Comparative analysis against classical machine learning models such as Support Vector Machine and Random Forest reveal a performance gap, where classical models are able to achieve perfect classification performance on the synthetic data. It is concluded that classical algorithms remain dominant in their ability to classify structured data with relatively simple class separations. However, due to the observed potential of certain VQC configurations to learn decision boundaries to classify data, their utility for future applications in noisier, higher-dimensional problems is highlighted.

quant-pharXiv:2610.34635•Oct 27, 2026•0 citations

Quantum Autoencoders for Network Anomaly Detection: A Comparative Benchmark with Classical Methods

Gönül ALTAY, Ecir Uğur Küçüksille

The practical value of quantum machine learning for network anomaly detection remains unclear under controlled and comparable benchmarking conditions. This study evaluates a trash-qubit-based Quantum Autoencoder (QAE) against seven classical anomaly-detection methods on UNSW-NB15 using shared data partitions, preprocessing steps, model selection procedures, and threshold calibration protocols. The experimental design included five independent seeds, three training set sizes, two feature budgets, and 12 QAE architectures, together with low-FPR analysis, finite-shot and synthetic-noise evaluation, less-constrained classical reference settings, and a cross-dataset assessment on TON_IoT. The Angle-RY encoding with a Real-Amplitudes Ring ansatz at depth L = 2 achieved the highest mean validation-selection AUPRC. On UNSW-NB15, the QAE was competitive in AUPRC and AUROC but remained behind the strongest classical baselines in F1-score, and its attack recall declined sharply under low-FPR constraints. The TON_IoT results further showed that relative model performance depended on the dataset. Under finite-shot and synthetic-noise conditions, anomaly-score rankings were largely preserved, whereas threshold-based decisions were more sensitive. Overall, the QAE showed competitive continuous-score discrimination on UNSW-NB15, but achieving reliable detection at low false-alarm rates remains a key operational challenge.

Electronics•Oct 1, 2026•0 citations
Abstract Edge anomaly detection in telemetry streams is constrained by tight energy budgets, fluctuating connectivity, and limited compute. This study evaluates quantum machine learning (QML) for such settings by integrating variational quantum circuits with an MQTT ingestion layer and an NS-3 network emulator. The approach combines hardware-efficient and QAOA-style ansätze with angle and amplitude encodings; stochastic gradient updates are performed via SPSA with measurement-shot scheduling tuned to network conditions. Methods include closed-loop simulation of packet loss, jitter, and delay across MQTT QoS tiers, followed by deployment-style inference profiling under device power caps. On synthetic yet representative workloads, the proposed QML detectors achieve competitive F1 relative to compact classical baselines (Δ≤3 percentage points), reduce energy per inference by 20–35% at matched accuracy, and meet p99 end-to-end latency targets under 40–45 ms for QoS-1/2 paths. Implications include a viable path to power-aware detection on constrained runtimes; limitations concern shot noise, small qubit counts, and transferability from simulation to hardware backends. Why it matters: coupling network-aware simulation with QML clarifies when variational circuits are Pareto-efficient on the edge. What’s inside: an MQTT/NS-3 harness, circuit/encoding recipes, training and calibration procedures, ablation studies on QoS and impairments, and deployment-oriented metrics (F1, energy/inference, p95/p99 latency). Keywords quantum machine learning, variational quantum circuits, hardware-efficient ansatz, QAOA, angle encoding, amplitude encoding, SPSA, MQTT, NS-3, edge anomaly detection, energy efficiency, latency profiling
Quantum Machine Learning (QML) unites quantum computing with modern AI to achieve potential gains in expressivity, runtime, and sample efficiency. This paper synthesizes advances in quantum feature maps, variational quantum circuits (VQCs), and hybrid quantum-classical workflows deployable on noisy intermediate-scale quantum (NISQ) hardware. We outline design principles for data encoding, ansatz selection, and trainability, and summarize error-aware practices—error mitigation, shot-frugal estimation, and compiler co-design. Using synthetic but instructive experiments, we illustrate scaling behavior, noise sensitivity, end-to-end inference latency across backends, and optimizer convergence in variational training. We conclude with an agenda emphasizing domain-aligned encodings, rigorous benchmarking, and reproducible open science to validate advantage beyond asymptotic claims.
This chapter develops variational quantum models as the dominant framework for near-term quantum machine learning (QML), emphasizing their role as trainable quantum circuits embedded within hybrid quantum-classical optimization loops. Building on earlier chapters on encoding and quantum feature geometry, it formulates parameterized quantum circuits (PQCs) as families of unitary transformations acting on reference states, with model outputs obtained through expectation values of observables. This measurement-based structure makes variational learning inherently stochastic and closely ties model behavior to circuit architecture, observable choice, and optimization strategy. This chapter examines variational quantum circuits (VQCs) as learning models, introduces quantum neural networks (QNNs) as structured variational architectures, and analyzes layered, data-reuploading, recurrent, and hybrid classical-quantum designs. It highlights the central tension between expressivity and trainability, showing how universality and approximation power are counterbalanced by optimization barriers such as barren plateaus. The discussion further develops ansatz design strategies, supervised, fidelity-based, and energy-based losses, regularization under noise, and practical methods for gradient estimation and optimization, including the parameter-shift rule, Simultaneous Perturbation Stochastic Approximation (SPSA), and layer-wise training. Together, these ideas establish variational quantum models as a flexible yet hardware-constrained paradigm whose practical success depends on careful coordination among architecture, measurement, and optimization.
Anomaly detection on high-dimensional tabular data requires models that are simultaneously compact, robust to noise, and interpretable, which are not met well by traditional ensemble learning approaches under strict parameter budgets. This work introduces NoiseAware-QML, a Variational Quantum Circuit (VQC) approach that incorporates a learnable noise parameterσ\sigmaσdirectly into the quantum ansatz, allowing the circuit to adaptively learn noise robustness during optimization through the reparameterization trick. The proposed 4-qubit, 4-layer VQC requires only 54 trainable parameters, a715×715 \times715×reduction over Random Forest and91×91 \times91×reduction over XGBoost, while maintaining a multi-seed mean ROC-AUC of0.8366±0.00830.8366 \pm 0.00830.8366±0.0083(95% CI: [0.8252, 0.8446]) on UNSW-NB15. Three robustness advantages with respect to parameter budget are formally established: (i) robustness to noise-1.84% AUC loss atσ=0.10\sigma=0.10σ=0.10compared to 4.12% for Random Forest (2.24× better) and 2.41% for a comparable-sized Dropout-MLP(1.31×(1.31 \times(1.31×better); (ii) calibration-ECE=0.0726\mathbf{E C E}=0.0726ECE=0.0726, improving over Random Forest (0.1127) and MLP (0.1151) by 36-37% without calibration correction; (iii) cross-dataset stability-only 5.36% AUC loss on NSL-KDD compared to 8.47% for Random Forest. Ablation study over three seeds verifies that adaptive noise regularization always improves over all variants by≈0.089\approx 0.089≈0.089AUC. Explainability through quantum-native means, per-gate gradientnorm heatmaps, and Bloch sphere analysis, demonstrates that the second-highest PCA variance component is actually harmful to anomaly detection, a result hidden from classical feature selection. Simulation-based deployment analysis confirms that the model generalizes to simulated NISQ hardware settings with AUC degradation of less than 2%.
The growing complexity of Internet of Things (IoT) networks has generated massive multivariate time-series data at the edge, challenging traditional forecasting and anomaly-detection models due to limited computation, memory, and energy on edge devices. Quantum machine learning (QML) provides a promising solution through expressive, parameter-efficient models that align with these constraints. This study proposes two distinct quantum-classical approaches for edge-based IoT analytics. The first combines a Quantum Neural Network (QNN) with a Quantum Autoencoder (QAE) to deliver lightweight forecasting and anomaly detection. The second employs Quantum Long Short-Term Memory (QLSTM) networks, exploring multiple variants and introducing optimization strategies to enable efficient deployment on a Raspberry Pi 5 using PennyLane simulators. Both approaches are evaluated on two real-world IoT datasets Bker (weather parameters) and ETTm1 (transformer temperature) and with a unified preprocessing pipeline incorporating normalization and PCA-based dimensionality reduction. Results show that QLSTM variants achieve superior forecasting accuracy, while QNN+QAE ensures robust anomaly detection with minimal resource overhead. A lightweight QLSTM variant strikes the best balance between accuracy and inference latency, enabling real-time edge deployment. To our knowledge, this is among the first practical demonstrations of QML-based forecasting and anomaly detection directly on edge hardware, highlighting a feasible pathway toward quantum-enhanced IoT intelligence.
The increasingly complex cybersecurity landscape requires more advanced network anomaly detection systems. Although, classical machine learning models are known to be effective, they reach computational bottlenecks when processing high-dimensional data. This study investigates the potential of Quantum Machine Learning (QML) for network traffic anomaly detection by evaluating four distinct Variational Quantum Classifier (VQC) architectures. A synthetic network traffic dataset is generated for the evaluations. The VQC models systematically varied feature encoding methods, parameterized ansatz circuits, quantum neural network types, and classical optimizers. Experimental results show that a trade-off exists between circuit expressivity and optimization stability. Deeper circuits (VQC-4) achieved higher accuracy of upto 89.0\%, while simultaneously being sensitive to training conditions. A shallower variant (VQC-1) under performed, although it had consistent and stable optimization curves. Class-dependent biases were also observed such as in VQC-2, where the model struggled to find an effective decision boundary, and produced a large number of false negatives. The best performing model in this study (VQC-3) combined ZFeatureMap with RealAmplitudes ansatz, optimized using ADAM. Comparative analysis against classical machine learning models such as Support Vector Machine and Random Forest reveal a performance gap, where classical models are able to achieve perfect classification performance on the synthetic data. It is concluded that classical algorithms remain dominant in their ability to classify structured data with relatively simple class separations. However, due to the observed potential of certain VQC configurations to learn decision boundaries to classify data, their utility for future applications in noisier, higher-dimensional problems is highlighted.
The practical value of quantum machine learning for network anomaly detection remains unclear under controlled and comparable benchmarking conditions. This study evaluates a trash-qubit-based Quantum Autoencoder (QAE) against seven classical anomaly-detection methods on UNSW-NB15 using shared data partitions, preprocessing steps, model selection procedures, and threshold calibration protocols. The experimental design included five independent seeds, three training set sizes, two feature budgets, and 12 QAE architectures, together with low-FPR analysis, finite-shot and synthetic-noise evaluation, less-constrained classical reference settings, and a cross-dataset assessment on TON_IoT. The Angle-RY encoding with a Real-Amplitudes Ring ansatz at depth L = 2 achieved the highest mean validation-selection AUPRC. On UNSW-NB15, the QAE was competitive in AUPRC and AUROC but remained behind the strongest classical baselines in F1-score, and its attack recall declined sharply under low-FPR constraints. The TON_IoT results further showed that relative model performance depended on the dataset. Under finite-shot and synthetic-noise conditions, anomaly-score rankings were largely preserved, whereas threshold-based decisions were more sensitive. Overall, the QAE showed competitive continuous-score discrimination on UNSW-NB15, but achieving reliable detection at low false-alarm rates remains a key operational challenge.