The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learning, model robustness and resilience to perturbations are well studied: deep neural networks (DNNs) maintain high performance despite pruning, noise injection, and structural perturbations due to inherent redundancy in their representations. A central challenge in quantum machine learning is to transfer this notion of robustness to quantum neural networks (QNNs) under realistic NISQ noise. While classical deep learning exhibits robustness through structural redundancy, analogous principles for QNNs remain underdeveloped. We propose JGRA: a framework for assessing robustness in noise-aware QNNs via Jacobian geometry, capturing model sensitivity to parameter perturbations induced by noise. Our method includes entropy-matched noise calibration, noise-aware training, and noise-conditioned Jacobian extraction, yielding geometric descriptors that link clean-regime structure to noisy inference behaviour. We also empirically demonstrate that these descriptors encode predictive information about robustness under unseen noise.
Comments
Accepted at IEEE qCCL 2026. Author accepted manuscript. 6 pages
The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learning, model robustness and resilience to perturbations are well studied: deep neural networks (DNNs) maintain high performance despite pruning, noise injection, and structural perturbations due to inherent redundancy in their representations. A central challenge in quantum machine learning is to transfer this notion of robustness to quantum neural networks (QNNs) under realistic NISQ noise. While classical deep learning exhibits robustness through structural redundancy, analogous principles for QNNs remain underdeveloped. We propose JGRA: a framework for assessing robustness in noise-aware QNNs via Jacobian geometry, capturing model sensitivity to parameter perturbations induced by noise. Our method includes entropy-matched noise calibration, noise-aware training, and noise-conditioned Jacobian extraction, yielding geometric descriptors that link clean-regime structure to noisy inference behaviour. We also empirically demonstrate that these descriptors encode predictive information about robustness under unseen noise.
uantum computing offers the potential to solve selected computational problems more efficiently than classical systems by leveraging quantum mechanical principles such as superposition and entanglement. However, current quantum devices operate in the noisy intermediatescale quantum (NISQ) regime, where limited coherence times, gate errors, measurement instability, and hardware variability significantly constrain practical performance. As a result, many quantum machine learning architectures that appear promising under idealized simulation conditions experience substantial degradation when executed under realistic noisy environments. This thesis investigates the problem of robustness in hybrid quantum neural network (HQNN) systems operating under realistic NISQ conditions. Rather than focusing primarily on quantum expressivity or claims of quantum advantage, the work examines whether practical hybrid quantum learning can maintain stable optimization and reliable inference in the presence of stochastic perturbations. A robustness-engineering framework is developed that integrates learned-readout decoding, multi-observable quantum feature extraction, architecture-level optimization, stability-aware training, and noise-augmented learning within a unified hybrid quantum-classical pipeline. To evaluate the framework, a comprehensive benchmarking methodology is developed across multiple datasets, architectures, perturbation environments, software frameworks, and hardware platforms. The experiments compare classical machine learning models, quantum kernel methods, and several HQNN architectures, including quanvolutional neural networks, quantum convolutional neural networks, and quantum transfer learning systems. Performance is evaluated under both noiseless and noisy conditions using standardized metrics, cross-noise validation, architecture-level comparisons, and real IBM Quantum hardware execution. The results demonstrate that baseline HQNN systems are highly sensitive to optimization instability, parity-based information loss, measurement variability, and perturbation accumulation. The experiments further reveal that robustness, rather than representational expressivity alone, is the dominant factor limiting practical hybrid quantum learning under realistic NISQ conditions. Through successive robustness-engineering stages, noisy performance improves from approximately 0.37 to 0.50 in baseline architectures to approximately 0.97 under several benchmark environments while maintaining substantially improved stability and reduced degradation under perturbation. These findings establish robustness as a central design objective for practical quantum machine learning. The thesis demonstrates that reliable hybrid quantum learning emerges through coordinated interaction between quantum feature generation, adaptive classical inference, stability-aware optimization, and hardware-aware architecture design. More broadly, the results suggest that hybrid quantum-AI systems are most effective when viewed as integrated quantum-classical computational frameworks in which quantum circuits function as probabilistic feature generators operating within larger robustness-oriented learning pipelines.
This work focuses on the design and evaluation of Hybrid Quantum Neural Networks (HQNNs) that integrate the computational advantages of quantum circuits with the learning flexibility of classical deep neural networks to enhance machine learning performance in the Noisy Intermediate-Scale Quantum (NISQ) era.The study investigates two prominent HQNN architectures, namely Quantum Convolutional Neural Networks (QCNNs) and Quanvolutional Neural Networks (QuanNNs), with an emphasis on their robustness under realistic quantum noise conditions.It was evaluated using image classification tasks.Under various quantum noise channels, including Bit Flip, Phase Flip, Phase Damping, Amplitude Damping, and Depolarizing Noise, were introduced to reflect realistic hardware conditions.To reduce noise-induced performance loss, error mitigation techniques such as Zero-Noise Extrapolation, Probabilistic Error Cancellation, and Measurement Error Mitigation were applied.In addition, an AI-assisted adaptive framework is proposed to automatically recommend suitable mitigation strategies based on observed noise behavior and circuit characteristics.Experimental results indicate that QuanNN exhibits strong robustness under lowto-moderate noise levels and maintains stable performance even under high bit-flip noise, while QCNN demonstrates occasional performance gains under specific noisy configurations but degrades more rapidly as noise intensity increases.The proposed AI-guided mitigation mechanism further enhances model stability across varying noise regimes.This study provides practical insights into architecture selection, noise resilience, and intelligent error mitigation integration, offering a scalable framework for deploying HQNNs in real-world NISQ-era quantum machine learning applications.
Quantum Neural Networks (QNNs) based on parameterized quantum circuits (PQCs) are gaining significant research attention due to their potential to achieve quantum advantages on Near-Term Noisy Intermediate-Scale Quantum (NISQ) computers. However, executing QNNs on NISQ devices is challenging due to quantum noise. To address this, we propose a noise-resilient QNN (NR-QNN) that leverages the unique characteristics of PQCs to perform noise-aware optimizations during the inference stage of QNNs. Specifically, NR-QNN employs two optimization techniques to mitigate the impact of noise on QNNs: quantum pruning and sensitivity-aware qubit mapping. The first technique is quantum pruning which identifies gates with small angle of rotations and removes them to simplify circuit of QNNs. The second optimization technique is sensitivity-aware qubit mapping which maps more important logical qubits to more reliable physical qubits. This technique is based on the observation that there can be variation in the sensitivity of an output to input qubits in a QNN. NR-QNN exploits this variability and guides qubit allocation to use reliable physical qubits for sensitive logical qubits. Our evaluation on a real quantum computer demonstrates that NR-QNN enhances the robustness of QNNs, enabling them to operate effectively on NISQ devices.
Quantum machine learning, crucial in the noisy intermediate-scale quantum (NISQ) era, confronts challenges in error mitigation. Current noise-aware training (NAT) methods often assume static error rates in quantum neural networks (QNNs), overlooking the dynamic nature of quantum noise. Our work highlights how error rates fluctuate over time and across different qubits, affecting QNN performance even when overall error rates are similar. We introduce a novel NAT strategy that dynamically adjusts to standard and fatal error conditions, incorporating a low-complexity search method to identify fatal errors during optimization. This strategy significantly improves robustness, maintaining competitive performance with leading NAT methods across varying error scenarios.
Abstract The rapid advancements in machine learning and quantum computing have given rise to a new research frontier: quantum machine learning. Quantum models designed for tackling classification problems possess the potential to deliver speed enhancements and superior predictive accuracy compared to their classical counterparts. However, recent research has revealed that quantum neural networks (QNNs), akin to their classical deep neural network-based classifier counterparts, are vulnerable to adversarial attacks. In these attacks, meticulously designed perturbations added to clean input data can result in QNNs producing incorrect predictions with high confidence. To mitigate this issue, we suggest enhancing the adversarial robustness of quantum machine learning systems by incorporating noise layers into QNNs. This is accomplished by solving a Min-Max optimization problem to control the magnitude of the noise, thereby increasing the QNN’s resilience against adversarial attacks. Extensive numerical experiments illustrate that our proposed method outperforms state-of-the-art defense techniques in terms of both clean and robust accuracy.
Hybrid Quantum Neural Networks (HQNNs) offer promising potential of quantum computing while retaining the flexibility of classical deep learning. However, the limitations of Noisy Intermediate-Scale Quantum (NISQ) devices introduce significant challenges in achieving ideal performance due to noise interference, such as decoherence, gate errors, and readout errors. This paper presents an extensive comparative analysis of two HQNN algorithms, Quantum Convolutional Neural Network (QCNN) and Quanvolutional Neural Network (QuanNN), assessing their noise resilience across diverse image classification tasks. We systematically inject noise into variational quantum circuits using five quantum noise channels: Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and Depolarizing Noise. By varying noise probabilities from 0.1 to 1.0, we evaluate the correlation between noise robustness and model behavior across different noise levels.Our findings demonstrate that different noise types and levels significantly influence HQNN performance. The QuanNN shows robust performance across most noise channels for low noise levels (0.1 - 0.4), but succumbs to diverse effects of depolarizing and amplitude damping noise at probabilities between (0.5 - 1.0). However, the QuanNN exhibits robustness to bit flip noise at high probabilities (0.9 - 1.0). On the other hand, the QCNN tends to benefit from the noise injection by outperforming noise-free models for bit flip, phase flip, and phase damping at high noise probabilities. However, for other noise types, the QCNN shows gradual performance degradation as noise increases. These insights aim to guide future research in error mitigation strategies to enhance HQNN models in the NISQ era.