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

arXiv:2606.24219

Decoherence as Defence and the Magnitude of Noise Regularisation: A Rigorous N -Qubit Theory of Stochastic Quantum Neural Networks for Adversarially Robust Network Intrusion Detection

Gautier-Edouard Filardo

Published Jun 23, 2026• 1 citation
arXivHTMLPDF

Abstract

Stochastic quantum neural networks (SQNNs) encode neuronal activations as qubits, synaptic topology as entanglement, and neural noise through a Lindblad master equation. A recent conference study applied a ring-entangled SQNN to collaborative intrusion detection and reached three conclusions: ring entanglement is \emph{essential} for non-local anomaly detection; an adversarial-resilience bound holds but is \emph{conservative}; and the depolarising channel \emph{fails} to act as a dropout-style regulariser, behaving instead as output noise. It left open whether a per-gate stochastic deactivation (``true quantum dropout'') could regularise where the depolarising channel could not, and whether the loose robustness bound could be replaced by a predictive theory. This paper resolves both and extends the framework to real data and to neutral-atom hardware. We give an $N$-qubit formulation through the stochastic master equation and its vectorised Liouvillian, and prove a \emph{decoherence-contraction theorem}: a depolarising channel of strength $γ$ over $L$ entangling layers contracts every weight-$w$ Pauli read-out by a factor $(1-4γ/3)^{wL}$ (for the weight-$1$ read-out used here, $(1-4γ/3)^{L}$); building on the general noise-as-defence result of Du et al., we make this quantitative and operational for intrusion detection. On the real NSL-KDD dataset under white-box FGSM and PGD attacks, a depolarising SQNN trained with the channel is, over seven seeds under strong $\ell_\infty$/$\ell_2$ attacks, significantly more robust than the noiseless circuit ($\ell_\infty$ PGD-$20$, $p=0.04$, large effect) and, critically, never suffers the catastrophic robustness collapse that the noiseless model and gradient-trained classical detectors (which fall from $95\%$ to $47\%$) do, cutting robustness variance roughly twofold; we show this robustness arises from a noise-reshaped training boundary rather than from attack-time gradient contraction. For generalisation, we derive an adaptive-penalty formula showing that per-gate dropout implements a curvature-weighted $L_2$ penalty $\tfrac{p(1-p)}{2}\sumθ^2\partial^2_θL$ in weight space, maximised at $p=1/2$, whereas depolarising noise implements an output-space penalty. A $30$-seed study confirms the formula's quantitative prediction: both mechanisms reduce the train-test gap by a small but statistically significant margin ($\approx\!0.01$; $p<10^{-4}$ and $p=0.004$), are statistically indistinguishable from each other, and the effect is concentrated where overfitting is largest; increasing the dropout rate past $1/2$ does not help, as the formula predicts. The single-seed dichotomy of prior work does not survive replication. We close with a neutral-atom realisation and a feasibility-by-$N$ analysis.

DOI
10.48550/arxiv.2606.24219

Related papers

gautierfilardo-efrei/sqnn-adversarial: v.1.1

gautierfilardo-efrei

Decoherence as Defence and the Magnitude of Noise Regularisation: A Rigorous N -Qubit Theory of Stochastic Quantum Neural Networks for Adversarially Robust Network Intrusion Detection

•Jun 21, 2026•0 citations

Stochastic Quantum Neural Networks for Collaborative Anomaly Detection in Distributed Enterprise Systems

Gautier-Edouard Filardo

Collaborative enterprise systems generate massive data streams requiring real-time anomaly detection. This paper extends our Stochastic Quantum Neural Network (QNNS) formalism to collaborative anomaly detection, leveraging superposition for parallel hypothesis testing, entanglement for inter-node correlation modeling, and stochastic noise for robustness. We validate three theoretical predictions through four experiments across two circuit scales (8 and 12 qubits), then quantify the theory–practice gap through bound tightness analysis, scaling diagnostics, and entanglement advantage decomposition. Our central result demonstrates that ring-topology entanglement is essential for detecting non-local correlations: on an XOR-structured anomaly dataset, ring entanglement achieves 84.5% accuracy versus 49.9% for circuits without entanglement (p < 0.01), with the ring closure alone accounting for +6.0% accuracy gain. The adversarial robustness bound |∆A| ≤ ϵ/(γ + ϵ) is satisfied at all test points, but tightness analysis reveals it overestimates vulnerability by 3–100×, characterizing it as a conservative safety guarantee rather than a tight prediction. A scaling study across 8-qubit (24 parameters) and 12-qubit (60 parameters) circuits reveals that the noise-as-regularization effect does not emerge at either scale; critically, the mean regularization deficit increases from +0.018 (8q) to +0.032 (12q) with a positive scaling slope, confirming a fundamental mechanism failure rather than a scale limitation. Together, these experiments and analyses transform the QNNS framework from a theoretical proposal to a partially validated architecture with precisely quantified strengths and honestly characterized limitations.

IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE)•Jul 1, 2026•0 citations

An Empirical Evaluation of Quantum Kernel Stability in Network Intrusion Detection

Sreejonty Chakraborty, Adrita Rahman Tory, Muhammad Aminur Rahaman +1 more

Quantum kernel methods have been proposed for network intrusion detection, yet their performance limitations are often attributed to noise in current quantum hardware. This study evaluates that assumption through a controlled analysis of Pegasos-QSVC on the NSL-KDD and ToN-IoT datasets. We perform 56 quantum experiments using one exact noiseless statevector backend and three noise-simulated superconducting backends while keeping preprocessing, PCA features, data splits, and classical baselines identical. XGBoost achieves accuracies of 98.94% on NSL-KDD and 99.41% on ToN-IoT, compared with 91.80% and 82.98% for Pegasos-QSVC. The quantum model also exhibits substantially greater seed-dependent variability. Eight runs collapse into degenerate classifiers, including four recall-collapse cases and four trivial-positive classifiers. Notably, two failures occur on the noiseless backend, demonstrating that hardware noise is not a necessary condition for classi-fier collapse. Kernel Gram matrix analysis further reveals low effective rank and severe ill-conditioning even in the absence of noise, indicating intrinsic fragility in the learned quantum representation. These results show that average accuracy alone can conceal operationally unacceptable behavior and highlight the importance of reporting worst-case performance, seed-level variability, class-specific metrics, and explicit degeneracy tests in quantum intrusion detection studies.

arXiv:2611.12219•Nov 9, 2026•0 citations

Quantum learning with noise and decoherence: a robust quantum neural network

Elizabeth Behrman, Nam Nguyen, James E. Steck

Noise and decoherence are two major obstacles to the implementation of large-scale quantum computing. Because of the no-cloning theorem, which says we cannot make an exact copy of an arbitrary quantum state, simple redundancy will not work in a quantum context, and unwanted interactions with the environment can destroy coherence and thus the quantum nature of the computation. Because of the parallel and distributed nature of classical neural networks, they have long been successfully used to deal with incomplete or damaged data. In this work, we show that our model of a quantum neural network (QNN) is similarly robust to noise, and that, in addition, it is robust to decoherence. Moreover, robustness to noise and decoherence is not only maintained but improved as the size of the system is increased. Noise and decoherence may even be of advantage in training, as it helps correct for overfitting. We demonstrate the robustness using entanglement as a means for pattern storage in a qubit array. Our results provide evidence that machine learning approaches can obviate otherwise recalcitrant problems in quantum computing.

•Dec 19, 2019•1 citation

Adversarial Robustness of Quantum Supervised Learning for Network Intrusion Detection: White-Box Attacks, PGD-Aware Training, and Classical Benchmarking

Rahul R. Bhoge, Dr.Ranjit Keole, Pravin Karde

Abstract Quantum supervised learning (QSL) is increasingly investigated for intrusion detection, yet its behavior under adversarial manipulation remains insufficiently characterized in network-security settings. This study presents a controlled white-box evaluation of a four-qubit variational QSL intrusion detector and a matched classical multilayer perceptron (MLP) on the UNSW-NB15 benchmark. Categorical encoding, standardization, principal component analysis to four dimensions, and scaling to [0, π] were applied consistently. A clean QSL model and a PGD-aware QSL model using 50% clean, 25% FGSM, and 25% PGD samples were evaluated against FGSM and seven-step PGD attacks at ε = 0.02π, 0.05π, and 0.10π over ten matched random seeds. Clean and adversarially trained MLP controls used the same representation and attack protocol. PGD-aware QSL improved accuracy over clean QSL from 9.10% to 26.90% at PGD 0.05π and from 2.60% to 20.73% at PGD 0.10π, with large paired effect sizes. The improvement was accompanied by a clean-accuracy reduction from 70.73% to 61.57%. Robust MLP retained higher absolute adversarial accuracy, reaching 64.27% and 50.50% at PGD 0.05π and 0.10π, respectively. The results demonstrate that adversarial training materially strengthens the tested QSL model but do not support a quantum-advantage claim. The study provides a reproducible robustness benchmark emphasizing attack validation, repeated seeds, effect sizes, and classical controls. The implementation notebook and supporting experimental outputs used for reproducibility are publicly archived on Zenodo (Bhoge et al. 2026).

•Oct 12, 2026•0 citations

Quantum learning with noise and decoherence: a robust quantum neural network

Nam H. Nguyen, Elizabeth Behrman, James E. Steck

Noise and decoherence are two major obstacles to the implementation of large-scale quantum computing. Because of the no-cloning theorem, which says we cannot make an exact copy of an arbitrary quantum state, simple redundancy will not work in a quantum context, and unwanted interactions with the environment can destroy coherence and thus the quantum nature of the computation. Because of the parallel and distributed nature of classical neural networks, they have long been successfully used to deal with incomplete or damaged data. In this work, we show that our model of a quantum neural network (QNN) is similarly robust to noise, and that, in addition, it is robust to decoherence. Moreover, robustness to noise and decoherence is not only maintained but improved as the size of the system is increased. Noise and decoherence may even be of advantage in training, as it helps correct for overfitting. We demonstrate the robustness using entanglement as a means for pattern storage in a qubit array. Our results provide evidence that machine learning approaches can obviate otherwise recalcitrant problems in quantum computing.

arXiv:1612.07593•Quantum Machine Intelligence•Jan 31, 2020•61 citations
Stochastic quantum neural networks (SQNNs) encode neuronal activations as qubits, synaptic topology as entanglement, and neural noise through a Lindblad master equation. A recent conference study applied a ring-entangled SQNN to collaborative intrusion detection and reached three conclusions: ring entanglement is \emph{essential} for non-local anomaly detection; an adversarial-resilience bound holds but is \emph{conservative}; and the depolarising channel \emph{fails} to act as a dropout-style regulariser, behaving instead as output noise. It left open whether a per-gate stochastic deactivation (``true quantum dropout'') could regularise where the depolarising channel could not, and whether the loose robustness bound could be replaced by a predictive theory. This paper resolves both and extends the framework to real data and to neutral-atom hardware. We give an NNN-qubit formulation through the stochastic master equation and its vectorised Liouvillian, and prove a \emph{decoherence-contraction theorem}: a depolarising channel of strength γγγ over LLL entangling layers contracts every weight-www Pauli read-out by a factor (1−4γ/3)wL(1-4γ/3)^{wL}(1−4γ/3)wL (for the weight-111 read-out used here, (1−4γ/3)L(1-4γ/3)^{L}(1−4γ/3)L); building on the general noise-as-defence result of Du et al., we make this quantitative and operational for intrusion detection. On the real NSL-KDD dataset under white-box FGSM and PGD attacks, a depolarising SQNN trained with the channel is, over seven seeds under strong ℓ∞\ell_\inftyℓ∞​/ℓ2\ell_2ℓ2​ attacks, significantly more robust than the noiseless circuit (ℓ∞\ell_\inftyℓ∞​ PGD-202020, p=0.04p=0.04p=0.04, large effect) and, critically, never suffers the catastrophic robustness collapse that the noiseless model and gradient-trained classical detectors (which fall from 95%95\%95% to 47%47\%47%) do, cutting robustness variance roughly twofold; we show this robustness arises from a noise-reshaped training boundary rather than from attack-time gradient contraction. For generalisation, we derive an adaptive-penalty formula showing that per-gate dropout implements a curvature-weighted L2L_2L2​ penalty p(1−p)2∑θ2∂θ2L\tfrac{p(1-p)}{2}\sumθ^2\partial^2_θL2p(1−p)​∑θ2∂θ2​L in weight space, maximised at p=1/2p=1/2p=1/2, whereas depolarising noise implements an output-space penalty. A 303030-seed study confirms the formula's quantitative prediction: both mechanisms reduce the train-test gap by a small but statistically significant margin (≈ ⁣0.01\approx\!0.01≈0.01; p<10−4p<10^{-4}p<10−4 and p=0.004p=0.004p=0.004), are statistically indistinguishable from each other, and the effect is concentrated where overfitting is largest; increasing the dropout rate past 1/21/21/2 does not help, as the formula predicts. The single-seed dichotomy of prior work does not survive replication. We close with a neutral-atom realisation and a feasibility-by-NNN analysis.
Collaborative enterprise systems generate massive data streams requiring real-time anomaly detection. This paper extends our Stochastic Quantum Neural Network (QNNS) formalism to collaborative anomaly detection, leveraging superposition for parallel hypothesis testing, entanglement for inter-node correlation modeling, and stochastic noise for robustness. We validate three theoretical predictions through four experiments across two circuit scales (8 and 12 qubits), then quantify the theory–practice gap through bound tightness analysis, scaling diagnostics, and entanglement advantage decomposition. Our central result demonstrates that ring-topology entanglement is essential for detecting non-local correlations: on an XOR-structured anomaly dataset, ring entanglement achieves 84.5% accuracy versus 49.9% for circuits without entanglement (p < 0.01), with the ring closure alone accounting for +6.0% accuracy gain. The adversarial robustness bound |∆A| ≤ ϵ/(γ + ϵ) is satisfied at all test points, but tightness analysis reveals it overestimates vulnerability by 3–100×, characterizing it as a conservative safety guarantee rather than a tight prediction. A scaling study across 8-qubit (24 parameters) and 12-qubit (60 parameters) circuits reveals that the noise-as-regularization effect does not emerge at either scale; critically, the mean regularization deficit increases from +0.018 (8q) to +0.032 (12q) with a positive scaling slope, confirming a fundamental mechanism failure rather than a scale limitation. Together, these experiments and analyses transform the QNNS framework from a theoretical proposal to a partially validated architecture with precisely quantified strengths and honestly characterized limitations.
Quantum kernel methods have been proposed for network intrusion detection, yet their performance limitations are often attributed to noise in current quantum hardware. This study evaluates that assumption through a controlled analysis of Pegasos-QSVC on the NSL-KDD and ToN-IoT datasets. We perform 56 quantum experiments using one exact noiseless statevector backend and three noise-simulated superconducting backends while keeping preprocessing, PCA features, data splits, and classical baselines identical. XGBoost achieves accuracies of 98.94% on NSL-KDD and 99.41% on ToN-IoT, compared with 91.80% and 82.98% for Pegasos-QSVC. The quantum model also exhibits substantially greater seed-dependent variability. Eight runs collapse into degenerate classifiers, including four recall-collapse cases and four trivial-positive classifiers. Notably, two failures occur on the noiseless backend, demonstrating that hardware noise is not a necessary condition for classi-fier collapse. Kernel Gram matrix analysis further reveals low effective rank and severe ill-conditioning even in the absence of noise, indicating intrinsic fragility in the learned quantum representation. These results show that average accuracy alone can conceal operationally unacceptable behavior and highlight the importance of reporting worst-case performance, seed-level variability, class-specific metrics, and explicit degeneracy tests in quantum intrusion detection studies.
Noise and decoherence are two major obstacles to the implementation of large-scale quantum computing. Because of the no-cloning theorem, which says we cannot make an exact copy of an arbitrary quantum state, simple redundancy will not work in a quantum context, and unwanted interactions with the environment can destroy coherence and thus the quantum nature of the computation. Because of the parallel and distributed nature of classical neural networks, they have long been successfully used to deal with incomplete or damaged data. In this work, we show that our model of a quantum neural network (QNN) is similarly robust to noise, and that, in addition, it is robust to decoherence. Moreover, robustness to noise and decoherence is not only maintained but improved as the size of the system is increased. Noise and decoherence may even be of advantage in training, as it helps correct for overfitting. We demonstrate the robustness using entanglement as a means for pattern storage in a qubit array. Our results provide evidence that machine learning approaches can obviate otherwise recalcitrant problems in quantum computing.
Abstract Quantum supervised learning (QSL) is increasingly investigated for intrusion detection, yet its behavior under adversarial manipulation remains insufficiently characterized in network-security settings. This study presents a controlled white-box evaluation of a four-qubit variational QSL intrusion detector and a matched classical multilayer perceptron (MLP) on the UNSW-NB15 benchmark. Categorical encoding, standardization, principal component analysis to four dimensions, and scaling to [0, π] were applied consistently. A clean QSL model and a PGD-aware QSL model using 50% clean, 25% FGSM, and 25% PGD samples were evaluated against FGSM and seven-step PGD attacks at ε = 0.02π, 0.05π, and 0.10π over ten matched random seeds. Clean and adversarially trained MLP controls used the same representation and attack protocol. PGD-aware QSL improved accuracy over clean QSL from 9.10% to 26.90% at PGD 0.05π and from 2.60% to 20.73% at PGD 0.10π, with large paired effect sizes. The improvement was accompanied by a clean-accuracy reduction from 70.73% to 61.57%. Robust MLP retained higher absolute adversarial accuracy, reaching 64.27% and 50.50% at PGD 0.05π and 0.10π, respectively. The results demonstrate that adversarial training materially strengthens the tested QSL model but do not support a quantum-advantage claim. The study provides a reproducible robustness benchmark emphasizing attack validation, repeated seeds, effect sizes, and classical controls. The implementation notebook and supporting experimental outputs used for reproducibility are publicly archived on Zenodo (Bhoge et al. 2026).
Noise and decoherence are two major obstacles to the implementation of large-scale quantum computing. Because of the no-cloning theorem, which says we cannot make an exact copy of an arbitrary quantum state, simple redundancy will not work in a quantum context, and unwanted interactions with the environment can destroy coherence and thus the quantum nature of the computation. Because of the parallel and distributed nature of classical neural networks, they have long been successfully used to deal with incomplete or damaged data. In this work, we show that our model of a quantum neural network (QNN) is similarly robust to noise, and that, in addition, it is robust to decoherence. Moreover, robustness to noise and decoherence is not only maintained but improved as the size of the system is increased. Noise and decoherence may even be of advantage in training, as it helps correct for overfitting. We demonstrate the robustness using entanglement as a means for pattern storage in a qubit array. Our results provide evidence that machine learning approaches can obviate otherwise recalcitrant problems in quantum computing.