Federated Learning (FL) enables privacy-preserving collaborative training but faces significant challenges when client data must be removed or malicious updates forgotten. Regulatory requirements and backdoor threats necessitate efficient, selective unlearning methods. However, existing approximate approaches modify large portions of model parameters, increasing vulnerability to gradient inversion attacks and degrading utility. We propose HQSU (Hybrid Quantum Selective Unlearning), a hybrid quantum-classical framework that performs selective unlearning via low-rank Hessian subspace modeling and variational quantum influence estimation. HQSU preserves 96.83% clean accuracy and reduces backdoor attack success to 9.95%, matching full retraining while modifying only 0.314% of parameters, over$300 \times$fewer than dense-update baselines. Experiments on MNIST show that HQSU achieves the lowest residual backdoor accuracy among approximate methods with stable recovery dynamics. Circuit ablations indicate that amplitude-encoded, circularly entangled ansätze provide the strongest influence estimation under NISQ constraints. These results demonstrate that hybrid quantum modeling can significantly improve selectivity, stability, and privacy in federated unlearning.
Federated Learning (FL) enables privacy-preserving collaborative training but faces significant challenges when client data must be removed or malicious updates forgotten. Regulatory requirements and backdoor threats necessitate efficient, selective unlearning methods. However, existing approximate approaches modify large portions of model parameters, increasing vulnerability to gradient inversion attacks and degrading utility. We propose HQSU (Hybrid Quantum Selective Unlearning), a hybrid quantum-classical framework that performs selective unlearning via low-rank Hessian subspace modeling and variational quantum influence estimation. HQSU preserves 96.83% clean accuracy and reduces backdoor attack success to 9.95%, matching full retraining while modifying only 0.314% of parameters, over300×fewer than dense-update baselines. Experiments on MNIST show that HQSU achieves the lowest residual backdoor accuracy among approximate methods with stable recovery dynamics. Circuit ablations indicate that amplitude-encoded, circularly entangled ansätze provide the strongest influence estimation under NISQ constraints. These results demonstrate that hybrid quantum modeling can significantly improve selectivity, stability, and privacy in federated unlearning.
In this study, A Quantum-Classical Federated Learning (QCFL) framework designed for skin cancer prediction is presented. It integrates classical convolutional neural networks with variational quantum circuits so that both quantum computing and deep learning can be used in decentralized, privacy-preserving environments. The functioning of the Federated Learning model includes a efficient optimization algorithm suitable for quantum environments in FL called SCAFFOLD, which handle client heterogeneity and non-IID data distributions modeled using Dirichlet sampling. The framework includes three ways of training normal training along with trigger-based and semantic-based backdoor attacks to understand demonstrating the susceptibility of federated skin cancer models to stealthy adversarial behaviors. To defend against such threats, multiple detection and mitigation strategies are evaluated, including Activation Clustering, Neural Cleanse, and Fine-Pruning. . Additionally, a novel approach for defense, Spectral Defense, is proposed and developed, based on the eigen-spectrum analysis of internal neural activations to detect and ultimately suppress backdoor behavior without recourse to clean validation data. Experimental results on this hybrid quantum-classical model prove improvement in classification performance, whereas the Spectral Defense framework provides significant attack success rates reduction with little degradation in model accuracy. This work provides a robust and scalable approach for deploying secure federated learning systems to adverse conditions for medical image analysis.
Quantum Federated Learning (QFL) inherits the core vulnerability of federated optimization to malicious clients, while also introducing an attack surface from variational circuit training and measurement-driven gradients. This work proposes a novel CircUit-Level backdoor Threat (CULT) model that formalizes four stealthy attacks by exploiting quantum-aware mechanisms, including Grover, Pauli, Bit-flip, and Sign-flip. By enabling malicious clients on both in-training and post-training surfaces, these attacks can critically undermine the learning process. We establish a rigorous theoretical foundation to demonstrate attack stealthiness under standard smoothness assumptions. Experiments on the MNIST and CIFAR-10 datasets with non-IID splits and varying fractions of malicious clients show that even a single malicious client can induce severe accuracy degradation under FedAvg aggregation. While popular defenses, including Krum, Multi-Krum, FoolsGold, FLGuardian, and Mud-HoG, reduce degradation in many regimes, they fail to eliminate worst-case failure cases, where accuracy drops up to 50\%. The experimental analysis further reveals that under the CULT model, malicious updates effectively mask their presence by staying close to benign norms, thereby helping attackers evade detection.
Federated learning (FL) is a widely used method for training machine learning (ML) models in a scalable way while preserving privacy (i.e., without centralizing raw data). Prior research shows that the risk of exposing sensitive data increases cumulatively as the number of iterations where a client's updates are included in the aggregated model increase. Attackers can launch membership inference attacks (MIA; deciding whether a sample or client participated), property inference attacks (PIA; inferring attributes of a client's data), and model inversion attacks (MI; reconstructing inputs), thereby inferring client-specific attributes and, in some cases, reconstructing inputs. In this paper, we mitigate risk by substantially reducing per client exposure using a quantum computing-inspired quadratic unconstrained binary optimization (QUBO) formulation that selects a small subset of client updates most relevant for each training round. In this work, we focus on two threat vectors: (i) information leakage by clients during training and (ii) adversaries who can query or obtain the global model. We assume a trusted central server and do not model server compromise. This method also assumes that the server has access to a validation/test set with global data distribution. Experiments on the MNIST dataset with 300 clients in 20 rounds showed a 95.2% per-round and 49% cumulative privacy exposure reduction, with 147 clients' updates never being used during training while maintaining in general the full-aggregation accuracy or even better. The method proved to be efficient at lower scale and more complex model as well. A CINIC-10 dataset-based experiment with 30 clients resulted in 82% per-round privacy improvement and 33% cumulative privacy.
Some machine learning models are known to memorize their training data, exposing them to membership inference at- tacks (MIAs) that infer whether a particular data sample was used during training. Such leakage poses serious privacy risks in sensitive domains such as security and healthcare, where membership alone can reveal protected information about an individual. Machine unlearning has been proposed as a remedy, allowing a model to “forget” withdrawn data with- out retraining from scratch. There is some evidence from re- cent works that quantum architectures such as hybrid quan- tum neural networks (HQNNs) along with unlearning meth- ods may be robust to MIAs. In this work, we audit gradient- ascent-based unlearning in HQNNs to assess how effectively forgetting happens when the model is subjected to a range of membership inference attacks. By training an HQNN that combines classical convolutional pre-processing, amplitude encoding, and a parameterized quantum circuit, and apply- ing class-level unlearning to forget a target class, we evalu- ate the unlearned model against metric-based attacks (loss, confidence, entropy, and modified entropy), and quantum at- tacks constructed from a variational quantum circuit and a quantum support vector machine. Our results show that the apparent success of unlearning is highly metric- and attack- dependent. In particular, fixed-threshold-based metric attacks seem to classify almost all forgotten class samples as non- members after unlearning. However, class-conditional area under the curve (AUC) remains above random guessing and relatively higher compared to the original model, indicating that the membership signal does not completely disappear for both the forgotten and retained classes. We observe a similar behavior with quantum attack models, even though the strength of the attacks is relatively weaker compared to metric-based ones. These findings highlight the importance of evaluating quantum unlearning against a diverse set of attacks and performance measures before concluding that privacy is preserved, and lay a foundation for systematically auditing unlearning methods in quantum machine learning models.
Quantum federated learning trains a quantum neural network (QNN) across nodes that hold quantum data, such as the states of quantum sensors. To forget data, unlearning methods for quantum models replay them, and federated unlearning from stored updates removes whole nodes only. Quantum data cannot be replayed, since a state is consumed when measured and cannot be cloned. We propose Shadow-based Data Erasure (SHADE), in which each node records a classical shadow of every training state, a few randomized single-qubit measurements taken at training time. The gradient and curvature of a QNN on a state are expectations of observables, so SHADE estimates them for the forget data from the shadows at any later parameters and removes their effect by a federated Newton correction. Only classical estimates cross the network. We prove that the shadow size needed for a target unlearning error grows exponentially in the size of the backward light cone of the measured observable and not in the number of qubits. In simulation with 50 nodes and on edge boards, SHADE matches the forget accuracy of retraining within 0.5 points, without replay and in under 0.2 s.
Privacy-preserving approaches are essential in health- care applications where sensitive data is involved. Federated learning (FL) has emerged as a widely adopted approach for collaboratively training decentralized models without sharing individual health records. However, ensuring privacy in health- care data, both during training and when clients exchange their models with a central server, remains a challenge. Bias, fairness, clients heterogeneity, and constrained computation are also challenging factors. To address this challenge, in this paper, a communication-efficient and privacy-preserving hybrid Federated learning (HFL) framework is specifically designed for mental healthcare applications. Two HFL approaches, namely Clustered Federated Learning (CFL) and Quantum Federated Learning (QFL), have been proposed. CFL focuses on leveraging the learning behaviour of clients and Conversely, QFL introduces a new phase to FL by incorporating a variational quantum classifier (VQC) for classification tasks. Angle encoding is used for a quantum state preparation to enhance data encoding and learning the quantum model. Experiments were conducted on independent and identically distributed (iid) and non-independent and identically distributed (non-iid) data to evaluate the performance of the proposed methods with state-of-the-art results available in the literature. The results demonstrate exceptional performance in the case of QFL, achieving an accuracy of 84.00%. CFL also exhibits promising results with an accuracy of 78.396%. Additionally, QFL achieves 18.75% better recall and CFL has 6.24% better precision than traditional FL. Nevertheless, it’s crucial to remember that every model has advantages and disadvantages of its own.