We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantum-augmented architectures remains largely unexplored. First, we adapt a broad suite of unlearning methods to quantum settings, including gradient-based, distillation-based, regularization-based and certified techniques. Second, we introduce two new unlearning strategies tailored to hybrid models. Experiments across Iris, MNIST, and Fashion-MNIST, under both subset removal and full-class deletion, reveal that quantum models can support effective unlearning, but outcomes depend strongly on circuit depth, entanglement structure, and task complexity. Shallow VQCs display high intrinsic stability with minimal memorization, whereas deeper hybrid models exhibit stronger trade-offs between utility, forgetting strength, and alignment with retrain oracle. We find that certain methods, e.g. EU-k, LCA, and Certified Unlearning, consistently provide the best balance across metrics. These findings establish baseline empirical insights into quantum machine unlearning and highlight the need for quantum-aware algorithms and theoretical guarantees, as quantum machine learning systems continue to expand in scale and capability. We publicly release our code at: https://github.com/CrivoiCarla/HQML.
We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantum-augmented architectures remains largely unexplored. First, we adapt a broad suite of unlearning methods to quantum settings, including gradient-based, distillation-based, regularization-based and certified techniques. Second, we introduce two new unlearning strategies tailored to hybrid models. Experiments across Iris, MNIST, and Fashion-MNIST, under both subset removal and full-class deletion, reveal that quantum models can support effective unlearning, but outcomes depend strongly on circuit depth, entanglement structure, and task complexity. Shallow VQCs display high intrinsic stability with minimal memorization, whereas deeper hybrid models exhibit stronger trade-offs between utility, forgetting strength, and alignment with retrain oracle. We find that certain methods, e.g. EU-k, LCA, and Certified Unlearning, consistently provide the best balance across metrics. These findings establish baseline empirical insights into quantum machine unlearning and highlight the need for quantum-aware algorithms and theoretical guarantees, as quantum machine learning systems continue to expand in scale and capability. We publicly release our code at: https://github.com/CrivoiCarla/HQML.
Machine unlearning aims to remove the influence of specific training data from a learned model without full retraining. While recent work has begun to explore unlearning in quantum machine learning, existing approaches largely rely on fixed, uniform target distributions and do not explicitly control the trade-off between forgetting and retained model behaviour. In this work, we propose a distribution-guided framework for class-level quantum machine unlearning that treats unlearning as a constrained optimization problem. Our method introduces a tunable target distribution derived from model similarity statistics, decoupling the suppression of forgotten-class confidence from assumptions about redistribution among retained classes. We further incorporate an anchor-based preservation constraint that explicitly maintains predictive behaviour on selected retained data, yielding a controlled optimization trajectory that limits deviation from the original model. We evaluate the approach on variational quantum classifiers trained on the Iris and Covertype datasets. Results demonstrate sharp suppression of forgotten-class confidence, minimal degradation of retained-class performance, and closer alignment with the gold retrained model baselines compared to uniform-target unlearning. These findings highlight the importance of target design and constraint-based formulations for reliable and interpretable quantum machine unlearning.
Quantum machine learning (QML) has the potential to achieve quantum advantage for specific tasks by combining quantum computation with classical machine learning (ML). In classical ML, a significant challenge is membership-privacy leakage, whereby an attacker can infer from model outputs whether specific data were used in training. When specific data are required to be withdrawn, removing their influence from the trained model becomes necessary. Machine unlearning (MU) addresses this issue by enabling the model to forget the withdrawn data, thereby preventing membership-privacy leakage. However, this leakage remains underexplored in QML. This raises two research questions: do QML models leak membership privacy about their training data, and can MU methods efficiently mitigate such leakage in QML models? We investigate these questions using two quantum neural network (QNN) architectures, a basic QNN and a hybrid QNN, evaluated in noiseless simulations and cloud quantum device demonstrations. To answer the first question, we analyze how quantum constraints shape membership-privacy leakage in QML and then formalize a realistic gray-box threat model accordingly. Based on this, we design a membership inference attack (MIA) tailored to QNN outputs, and our results provide clear evidence of membership leakage in both QNNs. To answer the second question, we propose a quantum machine unlearning (QMU) framework, comprising three MU mechanisms. Evaluations on two QNN architectures show that QMU removes the influence of the withdrawn data while preserving accuracy for retained data. A comparative analysis further characterizes the three MU mechanisms with respect to data dependence, computational cost, and robustness.
With the advancement of quantum computing in the Noisy Intermediate-Scale Quantum (NISQ) era, hybrid quantum-classical algorithms have emerged as promising approaches for addressing certain machine learning tasks. This study investigates the Variational Quantum Classifier (VQC), a hybrid model that integrates parameterized quantum circuits with classical optimization routines, implemented via IBM’s Qiskit framework. We provide a detailed account of the VQC architecture, including feature encoding, ansatz construction, and optimization methodology. To assess its performance, we conduct a comparative analysis between VQC and classical Support Vector Classifiers (SVC) across synthetic and real-world datasets, including Iris and a binary-filtered version of MNIST. Experimental results reveal that classical models consistently achieve higher accuracy and faster training times. However, the VQC demonstrates functional viability, particularly under noise-free conditions and reduced-dimensionality settings. These findings underscore the current limitations of quantum models while highlighting the potential of VQC as a proof-of-concept for quantum-enhanced learning as quantum hardware matures.
Quantum machine learning sits at the intersection of two paradigm-shifting technologies: quantum computing and deep learning. By exploiting quantum mechanical phenomena – superposition, entanglement, and interference – QML promises exponential or quadratic speedups over classical algorithms for certain learning tasks, as well as the ability to model quantum data natively. However, the path to practical quantum advantage remains contested, constrained by noisy intermediate-scale quantum (NISQ) hardware, limited qubit counts (50–1,000), coherence times (50–500 μs), and high gate error rates (10⁻³–10⁻⁴). This paper provides a rigorous, technically deep survey of QML: mathematical foundations (Hilbert spaces, unitary evolution, measurement, quantum circuits), canonical algorithms (quantum kernel methods, variational quantum circuits (VQCs), quantum neural networks (QNNs), QSVMs, quantum generative adversarial networks (QGANs), encoding strategies (angle, amplitude, basis, and Hamiltonian encoding), optimization landscapes (barren plateaus, parameter shift rules, ansatz design), hardware aware implementation on superconducting (IBM, Google), trapped ion (IonQ), and neutral atom (Pasqal) platforms, empirical benchmarks on near term devices for classification, generative modeling, and quantum chemistry, and pathways to fault tolerant quantum machine learning (FTQML) with error correction (surface codes, logical qubits). Researchers critically assess claims of quantum advantage, identify scenarios where QML may outperform classical ML (small data, high-dimensional feature spaces from quantum systems, kernel estimation), and propose concrete evaluation metrics (quantum-classical cross-validation, resource estimation).
Quantum Machine Learning (QML) has emerged as a compelling research domain that unites quantum computing principles with classical learning theory to address computationally demanding classification problems.This paper investigates two principal QML architectures-Variational Quantum Classifiers (VQC) and Quantum Neural Networks (QNN)-within the context of binary classification.We present an end-to-end hybrid quantum-classical pipeline applied to the UCI Mushroom dataset, comprising 22 categorical attributes, and demonstrate that quantumenhanced models can achieve competitive classification performance under present-day hardware constraints.The pipeline integrates Quantum Random Access Code (QRAC) encoding for dimensionality reduction, ZZFeatureMapbased quantum feature mapping, RealAmplitudes parameterized ansatz, and classical optimizer-driven parameter updates using the COBYLA algorithm.The complete system is deployed through a Flask web interface and containerized with Docker for reproducibility.Experimental results on a quantum simulator indicate a classification accuracy of 87.4%, precision of 0.891, and recall of 0.863, establishing the practical viability of NISQ-era quantum classifiers for structured categorical data.The paper further analyzes convergence behavior, circuit depth effects, and comparative performance against classical baselines, providing insights into the strengths and limitations of current QML architectures for real-world classification deployment.
Hybrid quantum-classical machine learning (HQML) models represent an emerging computational paradigm that combines the strengths of quantum computing and classical artificial intelligence to solve complex learning problems more efficiently.Quantum computing offers massive parallelism, superposition, and entanglement, enabling computational capabilities beyond classical systems for selected tasks.However, current quantum hardware remains limited by noise, decoherence, and scalability constraints.Hybrid architectures overcome these limitations by integrating quantum processors with classical machine learning frameworks, allowing practical implementation on Noisy Intermediate-Scale Quantum (NISQ) devices.This review paper presents a comprehensive study of hybrid quantum-classical machine learning models, including their architecture, working principles, quantum circuits, optimization techniques, and applications in healthcare, cybersecurity, finance, robotics, and big data analytics.The paper also discusses quantum neural networks, variational quantum circuits, quantum support vector machines, and quantum generative models.Furthermore, comparative analysis between classical and hybrid quantum systems is presented to evaluate performance, scalability, computational efficiency, and implementation challenges.Major issues such as quantum noise, hardware limitations, algorithm complexity, and high operational cost are examined in detail.Finally, future research directions and emerging trends in hybrid quantum-classical computing are discussed.The review concludes that HQML models have the potential to revolutionize next-generation intelligent computing systems.